{ "title": "The AI Toolchain — watchlist", "home_page_url": "https://aitoolchain.io/", "feed_url": "https://aitoolchain.io/tools.json", "updated": "2026-08-31T08:38:20.917525+00:00", "count": 133, "tools": [ { "tool": "Together AI", "category": "ai-infrastructure", "version": "changelog-20260831-07a75e81", "url": "https://docs.together.ai/docs/changelog", "open_source": false, "published_at": "2026-08-31T08:38:20.917525+00:00", "summary": "", "permalink": "https://aitoolchain.io/tools/together-ai" }, { "tool": "Kiro", "category": "ai-coding-agents", "version": "changelog-20260831-1c861324", "url": "https://kiro.dev/changelog", "open_source": false, "published_at": "2026-08-31T08:38:18.034095+00:00", "summary": "", "permalink": "https://aitoolchain.io/tools/kiro" }, { "tool": "LanceDB", "category": "vector-db-rag", "version": "docs-c2697346761b", "url": "https://lancedb.github.io/lancedb/python/python/", "open_source": true, "published_at": "2026-08-31T08:38:17.426673+00:00", "summary": "LanceDB adds sequence-packing for LLM training, list-element FTS granularity, GPU remote functions, and Azure direct-credential support.", "permalink": "https://aitoolchain.io/tools/lancedb" }, { "tool": "Fireworks AI", "category": "ai-infrastructure", "version": "docs-1421fbe74010", "url": "https://docs.fireworks.ai/updates/changelog", "open_source": false, "published_at": "2026-08-31T08:38:17.421324+00:00", "summary": "Fireworks AI adds DeepSeek V4 Flash 0731, Qwen 3.8 27B, and Muse Glimmer 30B to Serverless Training LoRA pool", "permalink": "https://aitoolchain.io/tools/fireworks-ai" }, { "tool": "Hermes", "category": "ai-agent-frameworks", "version": "docs-f98d2131295e", "url": "https://hermes-agent.nousresearch.com/docs/user-guide/configuration", "open_source": true, "published_at": "2026-08-31T08:38:17.410935+00:00", "summary": "Hermes adds database tuning, status-bar field selection, subagent request overrides, and WebSocket keepalive config keys.", "permalink": "https://aitoolchain.io/tools/hermes" }, { "tool": "Graphify", "category": "ai-coding-agents", "version": "docs-d59d1d4dc08e", "url": "https://graphify.com/changelog", "open_source": true, "published_at": "2026-08-31T08:38:17.407357+00:00", "summary": "Graphify v0.9.53 adds Robot Framework extraction support for .robot and .resource files", "permalink": "https://aitoolchain.io/tools/graphify" }, { "tool": "Groq", "category": "ai-infrastructure", "version": "snapshot-20260831", "url": "https://console.groq.com/docs/changelog#openai-gptoss-20b--openai-gptoss-120b", "open_source": false, "published_at": "2026-08-31T08:31:51.211113+00:00", "summary": "", "permalink": "https://aitoolchain.io/tools/groq" }, { "tool": "OpenAI", "category": "ai-infrastructure", "version": "snapshot-20260831", "url": "https://developers.openai.com/api/docs/guides/spend-limits", "open_source": false, "published_at": "2026-08-31T08:31:48.596507+00:00", "summary": "", "permalink": "https://aitoolchain.io/tools/openai" }, { "tool": "Daytona", "category": "ai-coding-agents", "version": "snapshot-20260831", "url": "https://daytona.io/changelog/org-members-command-and-client-side-http-timeout", "open_source": false, "published_at": "2026-08-31T08:31:30.272399+00:00", "summary": "", "permalink": "https://aitoolchain.io/tools/daytona" }, { "tool": "Superset", "category": "ai-coding-agents", "version": "desktop-v1.25.1", "url": "https://github.com/superset-sh/superset/releases/tag/desktop-v1.25.1", "open_source": false, "published_at": "2026-08-31T05:13:44+00:00", "summary": "Superset desktop v1.25.1 adds `superset scripts add`, PDF viewer, remote port forwarding, 14 new UI languages, workspace tags, and copy-on-select for terminals.", "permalink": "https://aitoolchain.io/tools/superset" }, { "tool": "OpenClaw", "category": "ai-agent-frameworks", "version": "v2026.8.1", "url": "https://github.com/openclaw/openclaw/releases/tag/v2026.8.1", "open_source": true, "published_at": "2026-08-31T03:30:51+00:00", "summary": "OpenClaw v2026.8.1 adds private credential requests, per-operation approval grants, team roles, shared credential store, external supervisor mode, and more.", "permalink": "https://aitoolchain.io/tools/openclaw" }, { "tool": "exxperts", "category": "ai-agent-frameworks", "version": "v0.11.0", "url": "https://github.com/EXXETA/exxperts/releases/tag/v0.11.0", "open_source": true, "published_at": "2026-08-31T03:30:04+00:00", "summary": "Exxperts v0.11.0 ships self-contained desktop and server archives with a vendored Node runtime — no Node, npm, or Git required on target machines.", "permalink": "https://aitoolchain.io/tools/exxperts" }, { "tool": "OpenAI Codex CLI", "category": "ai-coding-agents", "version": "rust-v0.152.0-alpha.6", "url": "https://github.com/openai/codex/releases/tag/rust-v0.152.0-alpha.6", "open_source": true, "published_at": "2026-08-31T02:12:53+00:00", "summary": "Codex CLI alpha.6 adds actionable rate-limit banners in the TUI and makes the `update_plan` tool opt-in via config.", "permalink": "https://aitoolchain.io/tools/openai-codex-cli" }, { "tool": "Cotool", "category": "ai-coding-agents", "version": "v0.66.0", "url": "https://docs.cotool.ai/changelog#v0-66-0", "open_source": false, "published_at": "2026-08-31T00:00:00+00:00", "summary": "Cotool v0.66.0 adds Cloudflare, Auth0, 1Password, and Tailscale integrations for investigation and alert triage.", "permalink": "https://aitoolchain.io/tools/cotool" }, { "tool": "vMLX", "category": "local-llm-runtime", "version": "v1.6.48", "url": "https://github.com/jjang-ai/vmlx/releases/tag/v1.6.48", "open_source": true, "published_at": "2026-08-30T22:41:17+00:00", "summary": "vMLX 1.6.48 enables vectorized GLM KDA MTP verification and makes native MTP restart cache proofs configurable", "permalink": "https://aitoolchain.io/tools/vmlx" }, { "tool": "Agno", "category": "ai-agent-frameworks", "version": "v3.0.4", "url": "https://github.com/agno-agi/agno/releases/tag/v3.0.4", "open_source": true, "published_at": "2026-08-30T22:40:41+00:00", "summary": "KnowledgeManagementTools gets granular opt-in flags and per-tool names; AtomicMail warm calls drop from ~35 s to under 3 s", "permalink": "https://aitoolchain.io/tools/agno" }, { "tool": "agentacct", "category": "ai-observability", "version": "v0.10.4", "url": "https://github.com/mikehasa/agentacct/releases/tag/v0.10.4", "open_source": true, "published_at": "2026-08-30T22:18:06+00:00", "summary": "agentacct v0.10.4 expands secret redaction to xAI, Groq, and Google OAuth tokens, and maps more agent tool names out of the 'other' bucket.", "permalink": "https://aitoolchain.io/tools/agentacct" }, { "tool": "xalgorix", "category": "exploitation", "version": "v4.6.5", "url": "https://github.com/xalgorix/xalgorix/releases/tag/v4.6.5", "open_source": true, "published_at": "2026-08-30T18:33:52+00:00", "summary": "xalgorix v4.6.5 adds opt-in Discord/Telegram scan-completion notifications via `XALGORIX_NOTIFY_SCAN_COMPLETE`", "permalink": "https://aitoolchain.io/tools/xalgorix" }, { "tool": "nono", "category": "ai-security", "version": "docs-59d9231c89bd", "url": "https://nono.sh/docs/cli/features/networking", "open_source": true, "published_at": "2026-08-30T14:37:59.816970+00:00", "summary": "nono adds `deny_domain` config key and `--deny-domain` CLI flag with three wildcard forms for fine-grained proxy blocking.", "permalink": "https://aitoolchain.io/tools/nono" }, { "tool": "gridctl", "category": "mcp-tooling", "version": "docs-bc4128d0269f", "url": "https://github.com/gridctl/gridctl/blob/main/README.md", "open_source": true, "published_at": "2026-08-30T14:37:59.812268+00:00", "summary": "gridctl adds scoped variable delivery with `var run`, `var explain`, and `var scan` commands for secrets and env-config management.", "permalink": "https://aitoolchain.io/tools/gridctl" }, { "tool": "DeepSeek Harness", "category": "ai-coding-agents", "version": "dsh-v0.1.2-alpha.2", "url": "https://github.com/deepseek-ai/deepseek-harness/compare/dsh-v0.1.2-alpha.1...dsh-v0.1.2-alpha.2", "open_source": true, "published_at": "2026-08-30T13:37:53+00:00", "summary": "DeepSeek Harness adds active reminders and schedules in session views, collapsed turn tails, and split usage/time stat pills in chat UI.", "permalink": "https://aitoolchain.io/tools/deepseek-harness" }, { "tool": "Doberman-Core", "category": "ai-security", "version": "v0.18.5", "url": "https://github.com/DobermanCore/Doberman-Core/releases/tag/v0.18.5", "open_source": true, "published_at": "2026-08-30T10:13:09+00:00", "summary": "Doberman-Core v0.18.5 adds log retention, version-check nudge, egress-threshold CLI, and richer doctor diagnostics", "permalink": "https://aitoolchain.io/tools/doberman-core" }, { "tool": "Qdrant", "category": "vector-db-rag", "version": "docs-428ce9dfc349", "url": "https://qdrant.tech/documentation/edge/edge-synchronization-guide/", "open_source": true, "published_at": "2026-08-30T08:37:05.803081+00:00", "summary": "Qdrant Edge gains a server synchronization guide covering dual-shard architecture, partial snapshots, and dual-write patterns.", "permalink": "https://aitoolchain.io/tools/qdrant" }, { "tool": "Arize Phoenix", "category": "ai-observability", "version": "docs-67bcffbb1525", "url": "https://arize.com/docs/phoenix/evaluation/pre-built-metrics", "open_source": true, "published_at": "2026-08-30T08:37:05.802495+00:00", "summary": "Arize Phoenix adds a PII Detection pre-built metric to screen conversation records for personally identifiable information.", "permalink": "https://aitoolchain.io/tools/arize-phoenix" }, { "tool": "Gemini API", "category": "ai-infrastructure", "version": "docs-0d7f72a672e5", "url": "https://ai.google.dev/gemini-api/docs/omni", "open_source": false, "published_at": "2026-08-30T08:37:05.801219+00:00", "summary": "", "permalink": "https://aitoolchain.io/tools/gemini-api" }, { "tool": "emisar", "category": "ai-infrastructure", "version": "docs-7e762a23d128", "url": "https://emisar.dev/docs/quickstart", "open_source": true, "published_at": "2026-08-30T08:37:05.798711+00:00", "summary": "emisar agents now ship with starter packs and a `sudo emisar status` health-check command.", "permalink": "https://aitoolchain.io/tools/emisar" }, { "tool": "Diagram Design", "category": "ai-coding-agents", "version": "commits-2026-08-11", "url": "https://github.com/cathrynlavery/diagram-design/compare/ec1b85f65d766f0a49def49fc007851cf0040f29...b52a33bfeef85d43995193ee52c13b485154b7b4", "open_source": true, "published_at": "2026-08-30T00:21:26+00:00", "summary": "Diagram Design gains Draw.io import, ten new diagram types, named client profiles, Pi support, and automatic plugin updates.", "permalink": "https://aitoolchain.io/tools/diagram-design" }, { "tool": "Zeroshot", "category": "ai-coding-agents", "version": "v6.46.0", "url": "https://github.com/the-open-engine/zeroshot/releases/tag/v6.46.0", "open_source": true, "published_at": "2026-08-29T23:03:50+00:00", "summary": "Zeroshot v6.46.0 adds keyed connection contracts and a supporting CLI surface.", "permalink": "https://aitoolchain.io/tools/zeroshot" }, { "tool": "ai-gateway", "category": "ai-observability", "version": "v1.5.0", "url": "https://github.com/ferro-labs/ai-gateway/releases/tag/v1.5.0", "open_source": true, "published_at": "2026-08-29T17:06:31+00:00", "summary": "ai-gateway v1.5.0 makes the gateway importable as a Go library via new run.Main() and run.Run() APIs", "permalink": "https://aitoolchain.io/tools/ai-gateway" }, { "tool": "ai-safe2-framework", "category": "ai-security", "version": "v3.1", "url": "https://github.com/CyberStrategyInstitute/ai-safe2-framework/releases/tag/v3.1", "open_source": true, "published_at": "2026-08-29T15:10:00+00:00", "summary": "AI SAFE² v3.1 adds 6 new MCP controls, three enforcement planes, protocol-independent persistence vocabulary, 12 new scanner rules, and a machine-readable manifest entry point for agents and bots.", "permalink": "https://aitoolchain.io/tools/ai-safe2-framework" }, { "tool": "mlx-serve", "category": "local-llm-runtime", "version": "v26.8.11", "url": "https://github.com/ddalcu/mlx-serve/releases/tag/v26.8.11", "open_source": true, "published_at": "2026-08-29T14:03:23+00:00", "summary": "mlx-serve v26.8.11 adds Qwen 3.8 Flash Next, multimodal video input, sparse attention kernels, and batch-concurrent inference.", "permalink": "https://aitoolchain.io/tools/mlx-serve" }, { "tool": "OntoCast", "category": "vector-db-rag", "version": "docs-494a122d95a5", "url": "https://growgraph.github.io/ontocast/reference/agent/update_common/", "open_source": true, "published_at": "2026-08-29T14:02:32.146262+00:00", "summary": "OntoCast gains `finalize_update_report` and `log_quarantine` in `ontocast.agent.update_common` for shared graph-patch hygiene.", "permalink": "https://aitoolchain.io/tools/ontocast" }, { "tool": "Helicone", "category": "ai-observability", "version": "docs-b7f548eb38ad", "url": "https://docs.helicone.ai/rest/ai-gateway/get-v1models-multimodal", "open_source": true, "published_at": "2026-08-29T14:02:32.143911+00:00", "summary": "Helicone exposes a `GET /v1/models/multimodal` endpoint on the AI Gateway to list supported multimodal models.", "permalink": "https://aitoolchain.io/tools/helicone" }, { "tool": "Braintrust", "category": "ai-observability", "version": "docs-373bbf59cffa", "url": "https://www.braintrust.dev/docs/changelog", "open_source": false, "published_at": "2026-08-29T14:02:32.143596+00:00", "summary": "Braintrust adds dashboards, bt trace CLI, MCP write tools, and new SDK capabilities across JS, Java, and Python", "permalink": "https://aitoolchain.io/tools/braintrust" }, { "tool": "Grok API", "category": "ai-infrastructure", "version": "docs-a503d241859b", "url": "https://docs.x.ai/llms.txt", "open_source": false, "published_at": "2026-08-29T14:02:32.143189+00:00", "summary": "Grok API adds Opus streaming for STT, SIP call transfer, batch image/video, multi-image generation, and audio-track control for video", "permalink": "https://aitoolchain.io/tools/grok-api" }, { "tool": "SGLang", "category": "local-llm-runtime", "version": "docs-352a5641aa79", "url": "https://docs.sglang.ai/docs/advanced_features/speculative_decoding", "open_source": true, "published_at": "2026-08-29T14:02:32.140446+00:00", "summary": "SGLang adds `--speculative-dsa-topk-backend` to independently control the DSA top-k backend for speculative draft workers.", "permalink": "https://aitoolchain.io/tools/sglang" }, { "tool": "camel-ai", "category": "ai-agent-frameworks", "version": "docs-a6d3ebf6bcf6", "url": "https://docs.camel-ai.org/mcp/camel_agents_as_an_mcp_clients", "open_source": true, "published_at": "2026-08-29T14:02:32.139828+00:00", "summary": "Adds `PulseMCPSearchToolkit` for searching MCP servers by keyword from within CAMEL agents", "permalink": "https://aitoolchain.io/tools/camel-ai" }, { "tool": "browser-use", "category": "ai-agent-frameworks", "version": "docs-f7a14be5a5b7", "url": "https://docs.browser-use.com/cloud/browser/playwright-puppeteer-selenium", "open_source": true, "published_at": "2026-08-29T14:02:32.139642+00:00", "summary": "browser-use Cloud adds a managed Chromium CDP API letting Playwright and Puppeteer connect to remote hardened browsers via `POST /api/v4/browsers`", "permalink": "https://aitoolchain.io/tools/browser-use" }, { "tool": "Letta", "category": "ai-agent-frameworks", "version": "docs-2492d21b5a90", "url": "https://docs.letta.com/configuration/schedules", "open_source": true, "published_at": "2026-08-29T14:02:32.138927+00:00", "summary": "Letta adds scheduled task CLI (`letta cron`) with cloud/local execution targets and conversation-binding options.", "permalink": "https://aitoolchain.io/tools/letta" }, { "tool": "bolt.new", "category": "ai-coding-agents", "version": "docs-821df3af7d1e", "url": "https://support.bolt.new/building/chat-tools", "open_source": false, "published_at": "2026-08-29T14:02:32.138234+00:00", "summary": "bolt.new adds a prompt queue supporting up to 20 queued prompts with reordering, pausing, and multi-user collaboration.", "permalink": "https://aitoolchain.io/tools/bolt-new" }, { "tool": "Hugging Face", "category": "ai-infrastructure", "version": "docs-6668b545a298", "url": "https://huggingface.co/docs/cli", "open_source": false, "published_at": "2026-08-29T14:02:32.137822+00:00", "summary": "Hugging Face CLI v1.29.0 adds bucket visibility controls, hardware discovery, and managed engine deployment with parallelism flags", "permalink": "https://aitoolchain.io/tools/hugging-face" }, { "tool": "Arcade", "category": "ai-agent-frameworks", "version": "docs-091b6c466d41", "url": "https://docs.arcade.dev/en/home", "open_source": false, "published_at": "2026-08-29T14:02:32.137426+00:00", "summary": "", "permalink": "https://aitoolchain.io/tools/arcade" }, { "tool": "OpenHands", "category": "ai-coding-agents", "version": "docs-c0969bd272b1", "url": "https://docs.openhands.dev/openhands/usage/agent-canvas/managing-automations", "open_source": true, "published_at": "2026-08-29T14:02:32.128275+00:00", "summary": "OpenHands automation runs now expose a live phase field and support Git sync for automations.", "permalink": "https://aitoolchain.io/tools/openhands" }, { "tool": "Pi", "category": "ai-coding-agents", "version": "docs-0bcb7463cd94", "url": "https://pi.dev/docs/latest/terminal-setup", "open_source": true, "published_at": "2026-08-29T14:02:32.126157+00:00", "summary": "Pi adds manual overrides for terminal capability detection via environment variables and JSON config keys.", "permalink": "https://aitoolchain.io/tools/pi" }, { "tool": "Replit Agent", "category": "ai-coding-agents", "version": "snapshot-20260829", "url": "https://docs.replit.com/updates", "open_source": false, "published_at": "2026-08-29T13:56:20.971586+00:00", "summary": "Replit Agent gains intelligent model routing, Growth Skills for customer acquisition, and custom OAuth connectors for Enterprise.", "permalink": "https://aitoolchain.io/tools/replit-agent" }, { "tool": "KoboldCpp", "category": "local-llm-runtime", "version": "v1.120", "url": "https://github.com/LostRuins/koboldcpp/releases/tag/v1.120", "open_source": true, "published_at": "2026-08-29T03:22:33+00:00", "summary": "KoboldCpp v1.120 adds DirectIO model loading, new model support for Qwen3.8-Flash-Next and Ling-3.0-flash, and custom JS tools in Kobold Lite.", "permalink": "https://aitoolchain.io/tools/koboldcpp" }, { "tool": "Darkbloom", "category": "ai-infrastructure", "version": "v0.8.15", "url": "https://github.com/Layr-Labs/d-inference/releases/tag/v0.8.15", "open_source": false, "published_at": "2026-08-29T02:11:17+00:00", "summary": "Darkbloom v0.8.15 adds opt-in JSON metadata on chat completions and integrates the Qwen3.8-27B VLM.", "permalink": "https://aitoolchain.io/tools/darkbloom" }, { "tool": "PydanticAI", "category": "ai-agent-frameworks", "version": "v2.36.0", "url": "https://github.com/pydantic/pydantic-ai/releases/tag/v2.36.0", "open_source": true, "published_at": "2026-08-29T01:25:08+00:00", "summary": "PydanticAI v2.36.0 adds `@durable_operation` for third-party durable execution, stable `InstructionPart.id`, async-iterable audio input, and `--mcp-config` support in `clai`.", "permalink": "https://aitoolchain.io/tools/pydanticai" }, { "tool": "Perplexity API", "category": "ai-infrastructure", "version": "changelog-20260828-02a9ef78", "url": "https://docs.perplexity.ai/changelog", "open_source": false, "published_at": "2026-08-28T20:21:49.292860+00:00", "summary": "Perplexity API adds GLM 5.3 model and automatic prompt cache keys for Agent API presets", "permalink": "https://aitoolchain.io/tools/perplexity-api" }, { "tool": "v0", "category": "ai-coding-agents", "version": "changelog-20260828-00d071ce", "url": "https://v0.app/changelog", "open_source": false, "published_at": "2026-08-28T20:21:48.073273+00:00", "summary": "v0 adds GPT-5.6 Sol, zero-config Vercel AI Gateway, 100 MCP servers per scope, and a redesigned invite/settings UI", "permalink": "https://aitoolchain.io/tools/v0" }, { "tool": "Modal", "category": "ai-infrastructure", "version": "docs-1d1df7717a9f", "url": "https://modal.com/docs/guide/sandbox-networking", "open_source": false, "published_at": "2026-08-28T20:21:45.319306+00:00", "summary": "Modal Sandboxes gain granular outbound/inbound network controls, runtime policy updates, and HTTP/WebSocket Connect Tokens.", "permalink": "https://aitoolchain.io/tools/modal" }, { "tool": "ai-memory", "category": "vector-db-rag", "version": "v1.34.0", "url": "https://github.com/akitaonrails/ai-memory/releases/tag/v1.34.0", "open_source": true, "published_at": "2026-08-28T19:32:00+00:00", "summary": "ai-memory v1.34.0 adds a dedicated `EMBEDDING_API_KEY`, a generic external-conversation importer with `--apply`, and the `workstreams` subcommand.", "permalink": "https://aitoolchain.io/tools/ai-memory" }, { "tool": "Composio", "category": "mcp-tooling", "version": "3.1.0", "url": "https://docs.composio.dev/openapi.json", "open_source": true, "published_at": "2026-08-28T18:29:32.353711+00:00", "summary": "API surface changed: +2 endpoints, 6 modified", "permalink": "https://aitoolchain.io/tools/composio" }, { "tool": "Augment Code", "category": "ai-coding-agents", "version": "0.2.0", "url": "https://www.augmentcode.com/openapi.json", "open_source": false, "published_at": "2026-08-28T18:29:28.168566+00:00", "summary": "Augment Code now publishes an API — 10 endpoints across 3 areas: Analytics, Budgets, Content", "permalink": "https://aitoolchain.io/tools/augment-code" }, { "tool": "Command Code", "category": "ai-coding-agents", "version": "v1.38.0", "url": "https://commandcode.ai/changelog#v1.38.0", "open_source": false, "published_at": "2026-08-28T18:24:41.860293+00:00", "summary": "Custom agents can now pin a reasoning effort level alongside their model selection", "permalink": "https://aitoolchain.io/tools/command-code" }, { "tool": "Claude Code", "category": "ai-coding-agents", "version": "v2.1.251", "url": "https://github.com/anthropics/claude-code/releases/tag/v2.1.251", "open_source": false, "published_at": "2026-08-28T18:19:32+00:00", "summary": "Claude Code v2.1.251 adds PreModelSwitch/PostModelSwitch hooks, subagent live streaming, spend-limit tracking, and prompt-cache cost reporting.", "permalink": "https://aitoolchain.io/tools/claude-code" }, { "tool": "Qwen Code", "category": "ai-coding-agents", "version": "v0.22.3", "url": "https://github.com/QwenLM/qwen-code/releases/tag/v0.22.3", "open_source": true, "published_at": "2026-08-28T17:16:38+00:00", "summary": "Qwen Code v0.22.3 adds named channel sessions, a `qwen review ab-drive` subcommand, standalone daemon session APIs, and a Mem0 extension skeleton.", "permalink": "https://aitoolchain.io/tools/qwen-code" }, { "tool": "LangChain", "category": "ai-agent-frameworks", "version": "langchain==1.4.0a2", "url": "https://github.com/langchain-ai/langchain/releases/tag/langchain%3D%3D1.4.0a2", "open_source": true, "published_at": "2026-08-28T16:19:22+00:00", "summary": "LangChain 1.4.0a2 ships `langchain.mcp`, a first-party adapter turning any MCP server into LangChain tools via `MCPAdapter`.", "permalink": "https://aitoolchain.io/tools/langchain" }, { "tool": "LM Studio", "category": "local-llm-runtime", "version": "changelog-20260828-15332d5f", "url": "https://lmstudio.ai/changelog/lmstudio", "open_source": false, "published_at": "2026-08-28T14:11:35.545759+00:00", "summary": "LM Studio 0.4.22 adds DFlash, DSpark, and MTP assistant drafters plus tool-returned image support in OpenAI and Anthropic APIs.", "permalink": "https://aitoolchain.io/tools/lm-studio" }, { "tool": "Warp", "category": "ai-coding-agents", "version": "changelog-20260828-2abdb525", "url": "https://docs.warp.dev/changelog/2026/", "open_source": false, "published_at": "2026-08-28T14:11:34.774748+00:00", "summary": "Warp Factories in Early Access, new `/usage` CLI command, IME input on Windows/Linux, and new right-click and '#' input settings.", "permalink": "https://aitoolchain.io/tools/warp" }, { "tool": "Devin Desktop", "category": "ai-coding-agents", "version": "changelog-20260828-5ce69e0e", "url": "https://windsurf.com/changelog", "open_source": false, "published_at": "2026-08-28T13:16:05.082074+00:00", "summary": "Devin Desktop adds multi-window agents, per-session URL copying, plan-mode Markdown files, and new ACP activity-sharing settings.", "permalink": "https://aitoolchain.io/tools/devin-desktop" }, { "tool": "Milvus", "category": "vector-db-rag", "version": "docs-7cb6d2f66ec6", "url": "https://milvus.io/docs/v2.5.x", "open_source": true, "published_at": "2026-08-28T13:16:02.462541+00:00", "summary": "Milvus 3.0 adds External Collection to index and query lake-resident data in place, without ingestion.", "permalink": "https://aitoolchain.io/tools/milvus" }, { "tool": "Anthropic", "category": "ai-infrastructure", "version": "docs-bee41fb88801", "url": "https://platform.claude.com/docs/en/api/beta/sessions", "open_source": false, "published_at": "2026-08-28T13:16:02.459843+00:00", "summary": "Anthropic beta Sessions API adds full CRUD plus multiagent, memory-store, and budget-limit capabilities for managed agent sessions.", "permalink": "https://aitoolchain.io/tools/anthropic" }, { "tool": "Cursor", "category": "ai-coding-agents", "version": "docs-bf7e858c38e8", "url": "https://cursor.com/docs/cloud-agent/api/endpoints", "open_source": false, "published_at": "2026-08-28T13:16:02.451549+00:00", "summary": "Cursor Cloud Agent API gains worker pools, SSE queue streaming, hibernation support, and a claim-release endpoint.", "permalink": "https://aitoolchain.io/tools/cursor" }, { "tool": "OpenCode", "category": "ai-coding-agents", "version": "docs-4d26cc069cec", "url": "https://opencode.ai/docs/providers", "open_source": true, "published_at": "2026-08-28T13:16:02.451088+00:00", "summary": "OpenCode adds Microsoft Entra ID (Azure CLI) authentication, enabling keyless access to Azure OpenAI and Foundry models via `az login`.", "permalink": "https://aitoolchain.io/tools/opencode" }, { "tool": "Goose", "category": "ai-coding-agents", "version": "docs-871a0f62f651", "url": "https://goose-docs.ai/docs/category/guides", "open_source": true, "published_at": "2026-08-28T13:16:02.448689+00:00", "summary": "Goose adds roaming agents, enabling remote access to a running agent from another machine over a network.", "permalink": "https://aitoolchain.io/tools/goose" }, { "tool": "Superlog", "category": "ai-observability", "version": "commits-2026-07-29", "url": "https://github.com/superloglabs/superlog/compare/93b552d11ed462d5c8742e538edee0a5b5350c25...cb3bf12602e808bd43f86c4ce4d6570087b6182d", "open_source": true, "published_at": "2026-08-28T13:07:40+00:00", "summary": "Superlog adds GCP disconnect, Cloudflare Workers selection, GCP log filters, Sentry webhook multiplexing, and MCP write-scope authoring tools.", "permalink": "https://aitoolchain.io/tools/superlog" }, { "tool": "OpenViking", "category": "vector-db-rag", "version": "v0.4.17", "url": "https://github.com/volcengine/OpenViking/releases/tag/v0.4.17", "open_source": true, "published_at": "2026-08-28T12:07:05+00:00", "summary": "OpenViking v0.4.17 adds inline content retrieval, MCP media blocks, private TOS imports, and an `ov-memory-doctor` diagnostic skill across Python/Go/TypeScript SDKs.", "permalink": "https://aitoolchain.io/tools/openviking" }, { "tool": "Langfuse", "category": "ai-observability", "version": "v4.23.0", "url": "https://github.com/langfuse/langfuse/releases/tag/v4.23.0", "open_source": true, "published_at": "2026-08-28T11:52:16+00:00", "summary": "Langfuse v4.23.0 adds stable evaluator API endpoints, dashboard S3 export, per-tool invocation metrics, and a sessions search bar.", "permalink": "https://aitoolchain.io/tools/langfuse" }, { "tool": "Semantica", "category": "ai-infrastructure", "version": "v0.6.7", "url": "https://github.com/semantica-agi/semantica/releases/tag/v0.6.7", "open_source": true, "published_at": "2026-08-28T10:28:34+00:00", "summary": "Semantica v0.6.7 adds LangChain integration, SAP OData ingestor, public SHACL validation API, reasoning Action layer, and ContextGraph Markdown persistence.", "permalink": "https://aitoolchain.io/tools/semantica" }, { "tool": "SkillSpector", "category": "ai-security", "version": "v2.11.0", "url": "https://github.com/NVIDIA/SkillSpector/releases/tag/v2.11.0", "open_source": true, "published_at": "2026-08-28T07:28:43+00:00", "summary": "SkillSpector v2.11.0 adds npm lockfile scanning, bundled hook findings (BH1–BH3), and LLM sampling controls via SKILLSPECTOR_TEMPERATURE and SKILLSPECTOR_SEED.", "permalink": "https://aitoolchain.io/tools/skillspector" }, { "tool": "AutoGPT", "category": "ai-agent-frameworks", "version": "autogpt-platform-beta-v0.7.3", "url": "https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.7.3", "open_source": true, "published_at": "2026-08-28T06:48:00+00:00", "summary": "AutoGPT Platform v0.7.3 adds a Briefing/Alert/Verdict/Ops email system, Copilot ask_question options, and live compaction progress in chat.", "permalink": "https://aitoolchain.io/tools/autogpt" }, { "tool": "Cline", "category": "ai-coding-agents", "version": "desktop-v0.0.20", "url": "https://github.com/cline/cline/releases/tag/desktop-v0.0.20", "open_source": true, "published_at": "2026-08-28T01:33:08+00:00", "summary": "Cline Desktop v0.0.20 ships a signed Windows installer, searchable session history, inline image rendering, and anchored agent schedules.", "permalink": "https://aitoolchain.io/tools/cline" }, { "tool": "HyperFrames", "category": "ai-infrastructure", "version": "v0.8.17", "url": "https://github.com/heygen-com/hyperframes/releases/tag/v0.8.17", "open_source": true, "published_at": "2026-08-28T00:44:38+00:00", "summary": "HyperFrames v0.8.17 exposes Studio live state to agentic browsers and adds a WebMCP polyfill for unsupported browsers.", "permalink": "https://aitoolchain.io/tools/hyperframes" }, { "tool": "Weights & Biases Weave", "category": "ai-observability", "version": "v0.53.7", "url": "https://github.com/wandb/weave/releases/tag/v0.53.7", "open_source": true, "published_at": "2026-08-27T21:35:08+00:00", "summary": "Weave v0.53.7 adds PII detection/redaction, an Agent PII policy field, and optional score-tracing control for imperative evals.", "permalink": "https://aitoolchain.io/tools/weights-biases-weave" }, { "tool": "Context Ontology Accelerator", "category": "vector-db-rag", "version": "v0.2.2", "url": "https://github.com/aws/context-ontology-accelerator/compare/v0.2.1...v0.2.2", "open_source": true, "published_at": "2026-08-27T21:26:15+00:00", "summary": "Adds an iterative NL→SQL agent, FK-aware ontology graph traversal, and `@pk`/@fk(...) constraint tags for Athena connectors.", "permalink": "https://aitoolchain.io/tools/context-ontology-accelerator" }, { "tool": "LangGraph", "category": "ai-agent-frameworks", "version": "sdk==0.4.4", "url": "https://github.com/langchain-ai/langgraph/releases/tag/sdk%3D%3D0.4.4", "open_source": true, "published_at": "2026-08-27T21:25:36+00:00", "summary": "LangGraph SDK 0.4.4 routes LangSmith traces from thread streams for deeper agent observability.", "permalink": "https://aitoolchain.io/tools/langgraph" }, { "tool": "CrewAI", "category": "ai-agent-frameworks", "version": "1.15.18", "url": "https://github.com/crewAIInc/crewAI/releases/tag/1.15.18", "open_source": true, "published_at": "2026-08-27T18:07:19+00:00", "summary": "CrewAI 1.15.18 promotes conversational flows to stable, adds declarative state/router config, and crew-style LLM config in chat declarations.", "permalink": "https://aitoolchain.io/tools/crewai" }, { "tool": "OpenShell", "category": "ai-security", "version": "v0.0.115", "url": "https://github.com/NVIDIA/OpenShell/releases/tag/v0.0.115", "open_source": true, "published_at": "2026-08-27T18:03:17+00:00", "summary": "OpenShell v0.0.115 adds native Windows MXC compute driver, OTLP trace export for Kubernetes, and OCI SBOM/provenance attestations.", "permalink": "https://aitoolchain.io/tools/openshell" }, { "tool": "GitHub Copilot CLI", "category": "ai-coding-agents", "version": "v1.0.81", "url": "https://github.com/github/copilot-cli/releases/tag/v1.0.81", "open_source": false, "published_at": "2026-08-27T17:10:08+00:00", "summary": "Copilot CLI v1.0.81 adds plugins dashboard, WAM auth, hooks trace context, `--with-token` login, per-agent usage metrics, and more.", "permalink": "https://aitoolchain.io/tools/github-copilot-cli" }, { "tool": "ToolHive", "category": "ai-security", "version": "v0.46.0", "url": "https://github.com/stacklok/toolhive/releases/tag/v0.46.0", "open_source": true, "published_at": "2026-08-27T17:04:19+00:00", "summary": "ToolHive v0.46.0 adds private-CA trust for embedded auth servers and signer-rotation blocking on plugin upgrades.", "permalink": "https://aitoolchain.io/tools/toolhive" }, { "tool": "Unsloth", "category": "ai-infrastructure", "version": "v0.1.804-beta", "url": "https://github.com/unslothai/unsloth/releases/tag/v0.1.804-beta", "open_source": true, "published_at": "2026-08-27T13:09:58+00:00", "summary": "Unsloth v0.1.804-beta adds Qwen3.8-Flash-Next and GLM-5.3-Flash local inference, JSONL chat export, sampling seed, and smarter GPU+RAM offloading.", "permalink": "https://aitoolchain.io/tools/unsloth" }, { "tool": "Weaviate", "category": "vector-db-rag", "version": "v1.38.13", "url": "https://github.com/weaviate/weaviate/releases/tag/v1.38.13", "open_source": true, "published_at": "2026-08-27T10:13:43+00:00", "summary": "Weaviate v1.38.13 adds a DigitalOcean generative module and export/import API endpoints for database user API-key hashes.", "permalink": "https://aitoolchain.io/tools/weaviate" }, { "tool": "mex", "category": "ai-coding-agents", "version": "v0.7.3", "url": "https://github.com/mex-memory/mex/compare/v0.7.2...v0.7.3", "open_source": true, "published_at": "2026-08-26T20:44:38+00:00", "summary": "mex v0.7.3 adds `mex graph repair` for in-place graph recovery and makes `mex check` fully read-only with staleness reporting.", "permalink": "https://aitoolchain.io/tools/mex" }, { "tool": "NeMo Guardrails", "category": "ai-security", "version": "v0.24.0", "url": "https://github.com/NVIDIA-NeMo/Guardrails/releases/tag/v0.24.0", "open_source": true, "published_at": "2026-08-26T19:31:04+00:00", "summary": "NeMo Guardrails v0.24.0 adds RailOutcome, rail manifests, F5 integration, health endpoints, and expands IORails to 59 built-in rails.", "permalink": "https://aitoolchain.io/tools/nemo-guardrails" }, { "tool": "Ollama", "category": "ai-infrastructure", "version": "v0.33.1", "url": "https://github.com/ollama/ollama/releases/tag/v0.33.1", "open_source": true, "published_at": "2026-08-26T18:09:57+00:00", "summary": "Ollama v0.33.1 adds structured output and Qwen3.8 Flash Next on the MLX backend, plus OLLAMA_HOST-aware Pi configuration.", "permalink": "https://aitoolchain.io/tools/ollama" }, { "tool": "Crush", "category": "ai-coding-agents", "version": "v0.91.2", "url": "https://github.com/charmbracelet/crush/releases/tag/v0.91.2", "open_source": true, "published_at": "2026-08-26T17:03:03+00:00", "summary": "Crush v0.91.2 adds three new Hyper models and automatic sessionless MCP support for GitHub MCP.", "permalink": "https://aitoolchain.io/tools/crush" }, { "tool": "Zed", "category": "ai-coding-agents", "version": "v1.17.2", "url": "https://github.com/zed-industries/zed/releases/tag/v1.17.2", "open_source": true, "published_at": "2026-08-26T15:25:08+00:00", "summary": "Zed v1.17.2 adds tabular CSV/TSV previews, new Git blame/stash actions, an agent `ask_user` tool, and a `simple` fullscreen mode.", "permalink": "https://aitoolchain.io/tools/zed" }, { "tool": "Claudoscope", "category": "uncategorized", "version": "v1.1.0", "url": "https://github.com/cordwainersmith/Claudoscope/releases/tag/v1.1.0", "open_source": true, "published_at": "2026-08-26T14:21:05+00:00", "summary": "Claudoscope v1.1.0 adds Insights, Hooks Runtime, Tasks & Jobs, Context, and six new config checks to its observability rails.", "permalink": "https://aitoolchain.io/tools/claudoscope" }, { "tool": "AI-Infra-Guard", "category": "ai-security", "version": "v4.6.0", "url": "https://github.com/Tencent/AI-Infra-Guard/releases/tag/v4.6.0", "open_source": true, "published_at": "2026-08-26T11:15:00+00:00", "summary": "AI-Infra-Guard v4.6.0 adds an API security audit module, LLM API poisoning detection, and a refactored agent red-team mutation engine.", "permalink": "https://aitoolchain.io/tools/ai-infra-guard" }, { "tool": "Pinecone", "category": "vector-db-rag", "version": "docs-d25d9691cf07", "url": "https://docs.pinecone.io/release-notes/2026", "open_source": false, "published_at": "2026-08-26T10:02:43.429131+00:00", "summary": "Pinecone BYOC reaches GA on AWS, GCP, and Azure; Pinecone Nexus knowledge engine for agents also now generally available", "permalink": "https://aitoolchain.io/tools/pinecone" }, { "tool": "LangSmith", "category": "ai-observability", "version": "docs-27faf7e6b490", "url": "https://docs.langchain.com/langsmith/data-export-destinations", "open_source": false, "published_at": "2026-08-26T10:02:43.428471+00:00", "summary": "LangSmith SaaS (GCP-hosted) can now export to S3 via AWS IAM role assumption, eliminating static credential storage.", "permalink": "https://aitoolchain.io/tools/langsmith" }, { "tool": "RunPod", "category": "ai-infrastructure", "version": "docs-c800be5f510b", "url": "https://docs.runpod.io/serverless/batch-jobs", "open_source": false, "published_at": "2026-08-26T10:02:43.427968+00:00", "summary": "RunPod Serverless adds Batch Jobs API for async bulk inference with dedicated workers, isolated from standard /run traffic", "permalink": "https://aitoolchain.io/tools/runpod" }, { "tool": "gemini-cli", "category": "ai-coding-agents", "version": "docs-665eb76f63cd", "url": "https://geminicli.com/docs/cli/skills/", "open_source": true, "published_at": "2026-08-26T10:02:43.427038+00:00", "summary": "Gemini CLI gains Agent Skills — installable, on-demand expertise bundles with scoped discovery and session management commands", "permalink": "https://aitoolchain.io/tools/gemini-cli" }, { "tool": "vLLM", "category": "local-llm-runtime", "version": "v0.28.0", "url": "https://github.com/vllm-project/vllm/releases/tag/v0.28.0", "open_source": true, "published_at": "2026-08-26T09:46:30+00:00", "summary": "vLLM v0.28.0 adds disk KV offloading, gRPC multimodal inference, new API fields, and major model/hardware expansions across NVIDIA, AMD, and Intel.", "permalink": "https://aitoolchain.io/tools/vllm" }, { "tool": "Giskard", "category": "ai-security", "version": "giskard-checks/v1.0.3", "url": "https://github.com/Giskard-AI/giskard-oss/releases/tag/giskard-checks/v1.0.3", "open_source": true, "published_at": "2026-08-26T08:39:15+00:00", "summary": "giskard-checks v1.0.3 lets `set_default_generator` accept model name strings in addition to generator objects.", "permalink": "https://aitoolchain.io/tools/giskard" }, { "tool": "holmesgpt", "category": "ai-agent-frameworks", "version": "0.40.0", "url": "https://github.com/HolmesGPT/holmesgpt/releases/tag/0.40.0", "open_source": true, "published_at": "2026-08-26T07:25:05+00:00", "summary": "HolmesGPT 0.40.0 adds personal skills, per-account skill hierarchy, tcp_check allowlists, and diagnostic-pod target policies.", "permalink": "https://aitoolchain.io/tools/holmesgpt" }, { "tool": "OpenWorker", "category": "ai-agent-frameworks", "version": "v0.2.1", "url": "https://github.com/andrewyng/openworker/compare/v0.2.0...v0.2.1", "open_source": true, "published_at": "2026-08-25T16:18:06+00:00", "summary": "Adds Ox Alpha stealth preview model via OpenRouter with 1,048,576-token context and tool calling support.", "permalink": "https://aitoolchain.io/tools/openworker" }, { "tool": "llama.cpp", "category": "local-llm-runtime", "version": "v0.3.0", "url": "https://github.com/ggml-org/llama.cpp/releases/tag/v0.3.0", "open_source": true, "published_at": "2026-08-25T10:22:58+00:00", "summary": "llama.cpp v0.3.0 adds dots3-note multimodal model, DeepSeek 4 tensor-split via `-sm tensor`, WebP support, and a new `LLAMA_SERVER_SLOTS_N_DIFF` debug env var.", "permalink": "https://aitoolchain.io/tools/llama-cpp" }, { "tool": "ONNX Runtime", "category": "ai-infrastructure", "version": "plugin-ep-webgpu/v0.3.0", "url": "https://github.com/microsoft/onnxruntime/releases/tag/plugin-ep-webgpu/v0.3.0", "open_source": true, "published_at": "2026-08-24T21:44:25+00:00", "summary": "ONNX Runtime WebGPU Plugin EP 0.3.0 adds new operators, quantized KV cache, int64/uint8 type expansion, and configurable buffer-cache options.", "permalink": "https://aitoolchain.io/tools/onnx-runtime" }, { "tool": "Haystack", "category": "ai-agent-frameworks", "version": "v3.1.0", "url": "https://github.com/deepset-ai/haystack/releases/tag/v3.1.0", "open_source": true, "published_at": "2026-08-24T15:19:09+00:00", "summary": "Haystack v3.1.0 adds context compaction hooks, token counters, AgentTool for multi-agent delegation, and a new HAYSTACK_UNSAFE_DESERIALIZATION env var.", "permalink": "https://aitoolchain.io/tools/haystack" }, { "tool": "Mend AI", "category": "ai-security", "version": "docs-9c324a68ae84", "url": "https://docs.mend.io/platform/latest/mend-ai-release-notes", "open_source": false, "published_at": "2026-08-24T14:58:16.333447+00:00", "summary": "", "permalink": "https://aitoolchain.io/tools/mend-ai" }, { "tool": "Certiv", "category": "ai-security", "version": "1.0.0", "url": "https://www.certiv.ai/openapi.json", "open_source": false, "published_at": "2026-08-23T10:11:56.498250+00:00", "summary": "Certiv now publishes an API — 2 endpoints across 1 area: Lead Capture", "permalink": "https://aitoolchain.io/tools/certiv" }, { "tool": "CalypsoAI", "category": "ai-security", "version": "10.62.4", "url": "https://docs.calypsoai.com/openapi.json", "open_source": false, "published_at": "2026-08-23T10:11:38.750493+00:00", "summary": "CalypsoAI now publishes an API — 141 endpoints across 28 areas: Projects, Users, Scanners, …", "permalink": "https://aitoolchain.io/tools/calypsoai" }, { "tool": "Promptfoo", "category": "ai-security", "version": "snapshot-20260823", "url": "https://www.promptfoo.dev/docs/releases/", "open_source": false, "published_at": "2026-08-23T09:42:15.966417+00:00", "summary": "Promptfoo snapshot-20260823 adds adaptive rate limiting, Transformers.js local inference, telecom red team plugins, and multi-input red team scanning.", "permalink": "https://aitoolchain.io/tools/promptfoo" }, { "tool": "DSPy", "category": "ai-agent-frameworks", "version": "3.3.1", "url": "https://github.com/stanfordnlp/dspy/releases/tag/3.3.1", "open_source": true, "published_at": "2026-08-21T23:07:09+00:00", "summary": "DSPy 3.3.1 adds managed Deno runtime for PythonInterpreter, multi-proposal GEPA optimization, structured MCP results, and expanded callback lifecycle visibility.", "permalink": "https://aitoolchain.io/tools/dspy" }, { "tool": "PromptLayer", "category": "ai-observability", "version": "snapshot-20260821", "url": "https://docs.promptlayer.com/changelog", "open_source": false, "published_at": "2026-08-21T09:52:38.338741+00:00", "summary": "PromptLayer adds trace I/O previews and a redesigned tabbed span details panel alongside Gemini 3.7 Flash support.", "permalink": "https://aitoolchain.io/tools/promptlayer" }, { "tool": "LocalAI", "category": "local-llm-runtime", "version": "v4.9.0", "url": "https://github.com/mudler/LocalAI/releases/tag/v4.9.0", "open_source": true, "published_at": "2026-08-20T15:59:49+00:00", "summary": "LocalAI 4.9.0: deny-by-default auth, chat context compression, KNN routing, PII pseudonyms, parallel HF downloads, and MiniMax-H3 video+audio", "permalink": "https://aitoolchain.io/tools/localai" }, { "tool": "Chroma", "category": "vector-db-rag", "version": "1.0.0", "url": "https://docs.trychroma.com/openapi.json", "open_source": true, "published_at": "2026-08-20T10:02:06.217071+00:00", "summary": "Chroma now publishes an API — 33 endpoints across 7 areas: Record, Collection, System, …", "permalink": "https://aitoolchain.io/tools/chroma" }, { "tool": "Mistral AI", "category": "ai-infrastructure", "version": "1.0.0", "url": "https://docs.mistral.ai/openapi.yaml", "open_source": false, "published_at": "2026-08-20T10:01:16.218277+00:00", "summary": "Mistral AI now publishes an API — 288 endpoints across 48 areas: (beta) Connectors API, Workflow Executions, (beta) Admin - User Groups, …", "permalink": "https://aitoolchain.io/tools/mistral-ai" }, { "tool": "Replicate", "category": "ai-infrastructure", "version": "snapshot-20260820", "url": "https://replicate.com/changelog", "open_source": false, "published_at": "2026-08-20T09:49:48.286714+00:00", "summary": "Replicate adds agent skills, MCP auto-discovery, prediction deadlines, fallback models, and source-filtered prediction listing.", "permalink": "https://aitoolchain.io/tools/replicate" }, { "tool": "LlamaIndex", "category": "ai-agent-frameworks", "version": "v0.14.24", "url": "https://github.com/run-llama/llama_index/releases/tag/v0.14.24", "open_source": true, "published_at": "2026-08-19T18:48:01+00:00", "summary": "LlamaIndex v0.14.24 adds Claude Opus 5/Sonnet 5, AG-UI multimodal input, async LLMRerank, and expanded VertexAI V2 API support.", "permalink": "https://aitoolchain.io/tools/llamaindex" }, { "tool": "herdr", "category": "ai-coding-agents", "version": "v0.8.2", "url": "https://github.com/herdrdev/herdr/releases/tag/v0.8.2", "open_source": true, "published_at": "2026-08-19T18:00:03+00:00", "summary": "herdr v0.8.2 adds Windows GA, Qwen Code support, remote attach, new config keys for window titles, tab bar status, and pane resize bindings", "permalink": "https://aitoolchain.io/tools/herdr" }, { "tool": "gram", "category": "mcp-tooling", "version": "dashboard@0.110.0", "url": "https://github.com/speakeasy-api/gram/releases/tag/dashboard%400.110.0", "open_source": true, "published_at": "2026-08-19T16:37:29+00:00", "summary": "gram dashboard 0.110.0 adds an AI research agent, graph-view MCP connections, drift detection for approved servers, and richer evidence dossiers.", "permalink": "https://aitoolchain.io/tools/gram" }, { "tool": "Docker Sandboxes", "category": "ai-security", "version": "v0.39.0", "url": "https://github.com/docker/sbx-releases/releases/tag/v0.39.0", "open_source": false, "published_at": "2026-08-19T10:42:00+00:00", "summary": "Docker Sandboxes v0.39.0 adds declarative `.sbxenv.yaml` environments, `sbx env` lifecycle commands, USB passthrough, bulk `sbx prune`, and kit signing via cosign.", "permalink": "https://aitoolchain.io/tools/docker-sandboxes" }, { "tool": "fenic", "category": "ai-infrastructure", "version": "v0.13.0", "url": "https://github.com/typedef-ai/fenic/releases/tag/v0.13.0", "open_source": true, "published_at": "2026-08-18T20:11:09+00:00", "summary": "fenic v0.13.0 adds Gemini 3.7 Flash support, drops Claude Opus 4.1, and extends Python compatibility to 3.13 and 3.14.", "permalink": "https://aitoolchain.io/tools/fenic" }, { "tool": "Semantic Kernel", "category": "ai-agent-frameworks", "version": "dotnet-1.80.0", "url": "https://github.com/microsoft/semantic-kernel/releases/tag/dotnet-1.80.0", "open_source": true, "published_at": "2026-08-18T15:00:38+00:00", "summary": "Gemini connector now honors FunctionChoiceBehavior function lists; MEVD providers migrated with redirect READMEs.", "permalink": "https://aitoolchain.io/tools/semantic-kernel" }, { "tool": "Object-Oriented Agents", "category": "ai-agent-frameworks", "version": "v0.0.9", "url": "https://github.com/NVIDIA-NeMo/labs-OO-Agents/releases/tag/v0.0.9", "open_source": true, "published_at": "2026-08-18T14:57:54+00:00", "summary": "OO Agents v0.0.9 adds entry-point CLI extensibility, a callable @strategy(llm=...), a portable journal exporter, shared interactive sessions, and a CyberGym portfolio agent.", "permalink": "https://aitoolchain.io/tools/object-oriented-agents" }, { "tool": "Adrian", "category": "ai-security", "version": "python-sdk-v1.2.0", "url": "https://github.com/secureagentics/Adrian/compare/python-sdk-v1.1.0...python-sdk-v1.2.0", "open_source": true, "published_at": "2026-08-18T14:09:12+00:00", "summary": "Adrian Python SDK v1.2.0 adds reasoning capture for LangChain and OpenAI-compatible models, including a new `reasoning` field in LLM events.", "permalink": "https://aitoolchain.io/tools/adrian" }, { "tool": "Old Coder", "category": "ai-coding-agents", "version": "commits-2026-07-27", "url": "https://github.com/AmazingAng/old-coder/compare/368a0ef35295fdefadf25de8f45bf2e1a1e5acbf...a0eb529d393a1cb3ccc564e32b2104e7e75c7a29", "open_source": true, "published_at": "2026-08-18T10:37:14+00:00", "summary": "Adds Java, Scala, SQL, and Emacs Lisp support; new source-state binding, fail-closed gauntlet orchestration, and PYTHONDONTWRITEBYTECODE mutation isolation.", "permalink": "https://aitoolchain.io/tools/old-coder" }, { "tool": "llmfit", "category": "local-llm-runtime", "version": "v1.1.10", "url": "https://github.com/AlexsJones/llmfit/releases/tag/v1.1.10", "open_source": true, "published_at": "2026-08-17T07:12:24+00:00", "summary": "llmfit v1.1.10 adds RamaLama runtime discovery via MCP and expands the model catalog with the Qwen3.8 family.", "permalink": "https://aitoolchain.io/tools/llmfit" }, { "tool": "OpenAI Agents SDK", "category": "ai-agent-frameworks", "version": "v0.21.1", "url": "https://github.com/openai/openai-agents-python/releases/tag/v0.21.1", "open_source": true, "published_at": "2026-08-16T22:28:55+00:00", "summary": "v0.21.1 adds model call timeouts, run-scoped sandbox working directories, Docker network isolation, and Modal resource options.", "permalink": "https://aitoolchain.io/tools/openai-agents-sdk" }, { "tool": "agent-safe-pipeline", "category": "ai-security", "version": "v0.1.0", "url": "https://github.com/decionis/agent-safe-pipeline/releases/tag/v0.1.0", "open_source": true, "published_at": "2026-08-15T15:46:02+00:00", "summary": "agent-safe-pipeline v0.1.0 introduces an agent-safe execution pipeline for controlled AI agent operations.", "permalink": "https://aitoolchain.io/tools/agent-safe-pipeline" }, { "tool": "vArmor", "category": "ai-security", "version": "v0.10.4", "url": "https://github.com/bytedance/vArmor/releases/tag/v0.10.4", "open_source": true, "published_at": "2026-08-13T06:54:45+00:00", "summary": "vArmor v0.10.4 adds egress audit-log persistence for Kata/micro-VMs, iptables backend auto-detection, and cluster-wide default sidecar resources via ConfigMap.", "permalink": "https://aitoolchain.io/tools/varmor" }, { "tool": "open-kritt", "category": "uncategorized", "version": "v1.4.0", "url": "https://github.com/Kritt-ai/open-kritt/releases/tag/v1.4.0", "open_source": true, "published_at": "2026-08-12T14:41:06+00:00", "summary": "open-kritt v1.4.0 adds a headless runner, scan findings export, steps binding, and memory-aware engine controls.", "permalink": "https://aitoolchain.io/tools/open-kritt" }, { "tool": "beelzebub", "category": "ai-security", "version": "v3.9.0", "url": "https://github.com/beelzebub-labs/beelzebub/releases/tag/v3.9.0", "open_source": true, "published_at": "2026-08-05T14:11:30+00:00", "summary": "Beelzebub v3.9.0 adds a ServicePlugin interface for boot-time background plugins, migrates plugin declarations to YAML config, and introduces shared JSON Schema validation for honeypot configurations.", "permalink": "https://aitoolchain.io/tools/beelzebub" }, { "tool": "EverOS", "category": "vector-db-rag", "version": "v1.2.2", "url": "https://github.com/EverMind-AI/EverOS/releases/tag/v1.2.2", "open_source": true, "published_at": "2026-08-05T05:35:53+00:00", "summary": "EverOS v1.2.2 adds a `cascade` health block on `GET /health` and the `everos cascade rebuild` recovery command for drifted or corrupt indexes.", "permalink": "https://aitoolchain.io/tools/everos" }, { "tool": "garak", "category": "ai-security", "version": "v0.16.0", "url": "https://github.com/NVIDIA/garak/releases/tag/v0.16.0", "open_source": true, "published_at": "2026-08-04T19:03:13+00:00", "summary": "garak v0.16.0 adds intent/technique-aware scanning, a native Anthropic generator, and an adaptive attacks probe", "permalink": "https://aitoolchain.io/tools/garak" }, { "tool": "City2Graph", "category": "ai-infrastructure", "version": "v1.0.0", "url": "https://github.com/c2g-dev/city2graph/releases/tag/v1.0.0", "open_source": true, "published_at": "2026-08-01T08:39:53+00:00", "summary": "City2Graph v1.0.0 adds morphological_graphs(), GBFS shared-mobility loading, and deprecates the `as_nx` parameter.", "permalink": "https://aitoolchain.io/tools/city2graph" }, { "tool": "ADR", "category": "ai-security", "version": "sensor-v1.0.0", "url": "https://github.com/uber/ADR/releases/tag/sensor-v1.0.0", "open_source": true, "published_at": "2026-07-31T18:42:14+00:00", "summary": "ADR Sensor v1.0.0: first public release of the Python telemetry package for Agentic Detection and Response", "permalink": "https://aitoolchain.io/tools/adr" }, { "tool": "Triton Inference Server", "category": "ai-infrastructure", "version": "v2.71.0", "url": "https://github.com/triton-inference-server/server/releases/tag/v2.71.0", "open_source": true, "published_at": "2026-07-29T16:09:26+00:00", "summary": "Triton v2.71.0 adds TensorRT multi-GPU inference, PyTorch 2 batching, NV embedding layers, and OpenAI frontend memory safeguards.", "permalink": "https://aitoolchain.io/tools/triton-inference-server" }, { "tool": "Knostic", "category": "ai-security", "version": "Introducing AgentMesh Access Tiers: Building Together, Growing Together (2026-07-27)", "url": "https://www.knostic.ai/blog/introducing-agentmesh-access-tiers", "open_source": false, "published_at": "2026-07-27T17:27:33+00:00", "summary": "AgentMesh moves to a freemium model with four access tiers, API access, and a bundled Kirin license at Premium and Pro.", "permalink": "https://aitoolchain.io/tools/knostic" }, { "tool": "Jan", "category": "local-llm-runtime", "version": "v0.8.4", "url": "https://github.com/janhq/jan/releases/tag/v0.8.4", "open_source": true, "published_at": "2026-07-23T06:29:15+00:00", "summary": "Jan v0.8.4 adds an OpenAI-compatible translating gateway, Responses API, native web search, per-model chat template kwargs, and migrates credentials to the OS keyring.", "permalink": "https://aitoolchain.io/tools/jan" } ] }