Heads up This site is currently under heavy development.
Subscribe Get it delivered — the daily firehose, filtered to the tools you run, plus the documentation changes vendors never announce. Compare plans →

The AI Toolchain — issue -093, May 18, 2026

THE AI TOOLCHAIN NO. -093
Tail
THE DAILY RELEASE FIREHOSE
PUBLISHED MAY 18, 2026 · EVERY WEEKDAY
EDITIONS tail grep head diff uniq

The daily firehose — everything the toolchain shipped today, already filtered.

// HOW THIS ISSUE IS MADE

We read every release from the 174 tools on our watchlist at the source — GitHub and GitLab release notes, vendor release pages and changelogs, project blogs and feeds, vendor press releases, and the source code behind the tag. Bug-fix-only releases and non-product newsroom noise are dropped; what's left is summarized down to the new capability, how to try it, and any screenshots or videos the release itself published. Every entry links to the sources it was built from.

VIEW
ISSUE VIEW full issue
Do you prefer this view?
$ tct list   # 6 tools matched
AI & LLM Tooling
◆  AI Agent Frameworks

CrewAI

Sources Release notes → 1.14.5 NOTES

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

CrewAI 1.14.5 adds state-restore kickoff, ExaSearchTool highlights, and Daytona sandbox improvements.

└──▷ GET THIS VERSION
$ git clone --branch 1.14.5 https://github.com/crewAIInc/crewAI.git
# already have the repo? check out this version:
$ git checkout 1.14.5
└──▷ USE IT
Resume a long-running Crew from a checkpoint state ID instead of restarting from scratch.
python
result = my_crew.kickoff(restore_from_state_id="<state_id>")
  • Adds restore_from_state_id kickoff parameter to resume a Crew run from a previously saved state.
  • Adds highlight results support to ExaSearchTool (formerly EXASearchTool).
  • Improves Daytona sandbox tool integration.
  • Defaults Crew agents to AgentExecutor, deprecating CrewAgentExecutor.
└──▷ BREAKING ON UPGRADE
  • !The EXASearchTool is renamed to ExaSearchTool; imports using the old name will break.
Was this useful?

OpenClaw

Sources Release notes → v2026.5.18 NOTES

Your own personal AI assistant. Any OS.

OpenClaw v2026.5.18 adds a meme-maker skill, Python/node debugger skills, typed plugin SDK, HTTPS proxy support, and Android realtime voice.

└──▷ GET THIS VERSION
$ git clone --branch v2026.5.18 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.5.18
└──▷ TRY IT
Scaffold a new typed tool plugin from scratch and validate its generated manifest before publishing.
$ openclaw plugins init my-tool && openclaw plugins build && openclaw plugins validate
Check runtime tool fixture coverage across Codex-native, OpenClaw dynamic, and plugin-backed tools as part of a CI release gate.
$ openclaw qa coverage --tools
Answer a pending browser modal dialog by ID when an automated browser action is blocked.
$ openclaw browser dialog --dialog-id <dialog-id> --action accept
  • Adds defineToolPlugin plus openclaw plugins build, validate, and init commands for authoring typed simple tool plugins with generated manifest metadata and context factories.
  • Adds a meme-maker skill supporting curated template search, local SVG/PNG rendering, Imgflip hosted rendering, and Know Your Meme provenance links.
  • Adds a Python debugging skill covering pdb, breakpoint(), post-mortem inspection, and debugpy remote attach.
  • Adds node inspector debugging, fused diagram generation, and throwaway spike workflow skills.
  • Switches Android Talk Mode to realtime Gateway relay voice sessions with streaming mic input, realtime audio playback, tool-result bridging, and on-screen transcripts.
+12 moreshow less
  • Supports HTTPS managed forward-proxy endpoints with scoped proxy.tls.caFile CA trust for proxy endpoint TLS.
  • Adds OPENCLAW_IMAGE_APT_PACKAGES as a runtime-neutral image build arg for extra apt packages (Docker/Podman), keeping OPENCLAW_DOCKER_APT_PACKAGES as a legacy fallback.
  • Surfaces pending and recently handled modal dialogs in browser snapshots, returns blockedByDialog when an action opens a modal, and adds browser dialog --dialog-id to answer pending dialogs.
  • Adds openclaw qa suite --runtime-parity-tier to wire the standard Codex-vs-Pi tier into release checks separately from optional/live-only/soak lanes.
  • Exposes runtime tool fixture coverage through openclaw qa coverage --tools with optional suite-summary evaluation for parity gate artifacts.
  • Allows trusted admin HTTP RPC clients to start and wait for web QR login flows.
  • Redesigns Mac app Settings pages with consistent card layouts, cached navigation, and cleaner permissions/voice/skills/cron/exec/debug panes.
  • Adds pnpm test:restart:gateway benchmark tooling for repeated restart readiness, downtime, trace, and resource-slope evidence.
  • Overlaps startup logging and plugin-service startup with channel sidecars to reduce restart ready latency while preserving /readyz sidecar gating.
  • Adds presentation capability limits for channel renderers and adapts rich message controls before native rendering.
  • Updates the Obsidian skill to target the official obsidian CLI and require its registered binary instead of the third-party obsidian-cli.
  • Renames the repo-local Codex closeout review skill and helper to autoreview while preserving the Codex-first fallback behavior.
└──▷ BREAKING ON UPGRADE
  • !The Obsidian skill now requires the official obsidian binary to be registered instead of the third-party obsidian-cli; setups using obsidian-cli will break.
  • !The repo-local Codex closeout review skill is renamed to autoreview; any config or scripts referencing the old skill name must be updated.
  • !The minimum supported Node.js 22 line is raised to 22.19; environments running an earlier 22.x patch will no longer be supported.
Was this useful?
◆  AI Coding Agents

Charm Crush

Sources Release notes → v0.70.0 NOTES

Glamourous agentic coding for all

Crush v0.70.0 adds Alibaba (Singapore) as a new AI provider and extends retries to cover network-level failures.

└──▷ GET THIS VERSION
$ git clone --branch v0.70.0 https://github.com/charmbracelet/crush.git
# already have the repo? check out this version:
$ git checkout v0.70.0
└──▷ TRY IT
Enable experimental client-server mode to support multiple sessions or remote Crush connections.
$ export CRUSH_CLIENT_SERVER=1
crush
  • Adds Alibaba (Singapore) as a new model provider, including access to Qwen models, configurable via the model picker or $ALIBABA_SINGAPORE_API_KEY.
  • Extends retry logic to cover network errors (e.g., transient offline states, DNS failures) in addition to HTTP error codes.
Was this useful?

OpenAI Codex CLI

Sources Release notes → rust-v0.131.0 NOTES

Lightweight coding agent that runs in your terminal

Codex CLI v0.131.0 adds codex doctor, unified @ mention picker, remote daemon control, marketplace plugin commands, and a richer TUI.

└──▷ GET THIS VERSION
$ git clone --branch rust-v0.131.0 https://github.com/openai/codex.git
# already have the repo? check out this version:
$ git checkout rust-v0.131.0
└──▷ TRY IT
Run environment-wide diagnostics before filing a support ticket or debugging auth/network issues.
$ codex doctor
  • Adds codex doctor command for support-ready diagnostics covering runtime, auth, terminal, network, config, and local state.
  • Unified @ mention picker now searches files, directories, plugins, and skills in a single interface backed by app-server plugin metadata.
  • Remote workflows gain codex remote-control daemon management, runtime enable/disable APIs, status reads, and registry-backed remote environments.
  • Plugin system adds marketplace CLI commands, version-aware sharing, share checkout, shared-workspace buckets, and default-enabled plugin hooks.
  • TUI gains data-driven service-tier slash commands, blended token usage display, permissions/approval mode visibility, effective workspace roots, and responsive Markdown tables.
+8 moreshow less
  • Python SDK renamed to openai-codex / openai_codex, with pinned runtime-generated types, concurrent turn routing by ID, and approval modes.
  • Adds Windows deny-read sandbox parity matching existing macOS/Linux sandbox behavior.
  • Adds Windows hook command overrides for customizing hook behavior per-platform.
  • Supports PreToolUse updatedInput rewrites, allowing hooks to modify tool inputs before execution.
  • Supports multi-environment apply_patch selection for applying patches across multiple configured environments.
  • TUI keymap config now accepts minus as a key binding value.
  • Adds ambient terminal pets to the TUI.
  • Exec-server now uses protobuf relay frames for transport.
Was this useful?

SST OpenCode

Sources Release notes → v1.15.5 NOTES

The open source coding agent.

OpenCode v1.15.5 adds --replay flags for session history, experimental native OpenAI runtime, and desktop notifications.

└──▷ GET THIS VERSION
$ git clone --branch v1.15.5 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v1.15.5
└──▷ TRY IT
Resume a session and review the last N exchanges before continuing — useful for picking up context after an interruption.
$ opencode --replay --replay-limit 10
  • Adds --replay and --replay-limit CLI flags to display recent session history when resuming interactive runs.
  • Previews a native OpenAI runtime path behind an experimental flag.
  • Enables desktop notifications from the renderer in the Desktop app.
  • Adds free-limit and usage-exceeded dialogs in the Desktop app.
  • Speeds up rendering of large session timelines in Desktop.
Was this useful?
Other / Uncategorized
◆  VECTOR DB RAG

LanceDB

Sources Release notes → v0.29.1-beta.0 2 RELEASES · 2026-05-18 NOTES STABLE

LanceDB v0.29.1-beta.0 adds namespace management, streaming ingestion, LSM write spec, and unenforced primary keys for Node.js and Python.

└──▷ GET THIS VERSION
$ git clone --branch v0.29.1-beta.0 https://github.com/lancedb/lancedb.git
# already have the repo? check out this version:
$ git checkout v0.29.1-beta.0
└──▷ USE IT
Use bytes literals in filter expressions when querying tables that store binary fields.
python
import lancedb
table.search().where(lancedb.lit(b'\x00\x01\x02') == table['payload']).to_list()
  • Adds Connection.renameTable in the Node.js SDK with namespace support.
  • Adds order_by method to Query in the Node.js SDK for sorted query results.
  • Exposes connectNamespace for namespace-backed connections in the Node.js SDK.
  • Adds namespace management methods on Connection in the Node.js SDK.
  • Adds Scannable primitive to the Node.js SDK for streaming data ingestion.
+4 moreshow less
  • Supports bytes values in lit() expressions in the Python SDK.
  • Adds public take_offsets method on Permutation in the Python SDK.
  • Supports setting an unenforced primary key on a table.
  • Supports setting the LSM write spec for a table.
1 more release in this issue · 2026-05-18
python-v0.32.1-beta.0 NOTES STABLE

LanceDB python-v0.32.1-beta.0 adds namespace management, streaming ingestion, bytes in lit(), unenforced primary keys, and LSM write spec support.

└──▷ GET THIS VERSION
$ git clone --branch python-v0.32.1-beta.0 https://github.com/lancedb/lancedb.git
# already have the repo? check out this version:
$ git checkout python-v0.32.1-beta.0
└──▷ USE IT
Return query results in a defined order using the new order_by method in the Node.js client.
javascript
const results = await table
  .query()
  .order_by([{ column: 'score', ascending: false }])
  .toArray();
  • Adds bytes support in lit() expressions for Python, enabling byte-literal predicates in filter expressions.
  • Adds take_offsets as a public method on Permutation in the Python API for direct offset-based row retrieval.
  • Adds namespace management methods on Connection in the Node.js API, plus connectNamespace for namespace-backed connections.
  • Adds Connection.renameTable with namespace support in the Node.js API.
  • Adds order_by method to Query in the Node.js API for sorted result sets.
+3 moreshow less
  • Adds Scannable primitive in the Node.js API for streaming ingestion workflows.
  • Supports setting an unenforced primary key on a table.
  • Supports setting the LSM write spec for a table.
Was this useful?
my-toolchain — 0 tools
paste an install list to detect your tools

A brew list, a Brewfile, requirements.txt, a Dockerfile — or just the product names, free-form. Nothing leaves your browser.

    browse all tools →