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.
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
Claude Code v2.1.105 adds PreCompact hooks, plugin background monitors, worktree path switching, and a smarter /doctor with auto-fix.
└──▷ GET THIS VERSION
$ git clone --branch v2.1.105 https://github.com/anthropics/claude-code.git
# already have the repo? check out this version:$ git checkout v2.1.105
└──▷ TRY IT
Block compaction at a critical point in a long session by returning a structured decision from a PreCompact hook.
$ #!/usr/bin/env sh
# .claude/hooks/pre-compact.sh
# Exit code 2 tells Claude Code to block compaction
exit 2
›Adds path parameter to the EnterWorktree tool to switch into an existing worktree of the current repository.
›Adds PreCompact hook support: hooks can block compaction by exiting with code 2 or returning {"decision":"block"}.
›Adds background monitor support for plugins via a top-level monitors manifest key that auto-arms at session start or on skill invoke.
›Adds /proactive as an alias for /loop.
›Improves /doctor layout with status icons and adds f keypress to have Claude automatically fix reported issues.
+3 moreshow less
›Raises plugin skill description listing cap from 250 to 1,536 characters, with a startup warning when descriptions are truncated.
›Improves WebFetch to strip <style> and <script> contents from fetched pages, preventing CSS-heavy pages from exhausting the content budget.
›Improves MCP large-output truncation prompt with format-specific recipes (e.g. jq for JSON, computed Read chunk sizes for text).
Pi v0.67.1 adds full OpenRouter routing config in models.json and a new env var for subprocess detection.
└──▷ GET THIS VERSION
$ git clone --branch v0.67.1 https://github.com/earendil-works/pi.git
# already have the repo? check out this version:$ git checkout v0.67.1
└──▷ USE IT
Route a model through OpenRouter with fallback providers, ZDR, and a max price cap — useful when you need data-residency guarantees or cost control in a shared team setup.
json
# In models.json, add an openRouterRouting block to your model entry:
{
"id": "my-model",
"openRouterRouting": {
"fallbacks": ["openai/gpt-4o", "anthropic/claude-3-5-sonnet"],
"dataCollection": false,
"zdr": true,
"maxPrice": { "prompt": 0.01, "completion": 0.03 },
"order": ["Fireworks", "Together"]
}
}
Detect inside a shell script or tool invoked by Pi that the process is running under the Pi coding agent.
$ if [ "$PI_CODING_AGENT" = "true" ]; then
echo "Running inside Pi coding agent — skipping interactive prompts"
fi
›Adds full openRouterRouting field support in models.json, enabling fallbacks, parameter requirements, data collection, ZDR, ignore lists, quantizations, provider sorting, max price, and preferred throughput/latency constraints.
›Sets PI_CODING_AGENT=true at startup so subprocesses and scripts can detect they are running inside the Pi coding agent.
›Adds anonymous install/update telemetry ping (only in interactive mode) to count per-version adoption; disable via /settings → Install telemetry, enableInstallTelemetry: false in settings.json, PI_OFFLINE=1, or PI_TELEMETRY=0.
Pi v0.67.0 adds full OpenRouter routing control in models.json and a PI_CODING_AGENT env flag for subprocess detection.
└──▷ GET THIS VERSION
$ git clone --branch v0.67.0 https://github.com/earendil-works/pi.git
# already have the repo? check out this version:$ git checkout v0.67.0
└──▷ TRY IT
Detect from a shell script or subprocess that Pi is orchestrating the run, so you can branch logic accordingly.
$ if [ "$PI_CODING_AGENT" = "true" ]; then
echo "Running inside Pi coding agent — skipping interactive prompts"
fi
›Adds full openRouterRouting field support in models.json, enabling fallbacks, parameter requirements, data collection, ZDR, ignore lists, quantizations, provider sorting, max price, and preferred throughput/latency constraints.
›Sets PI_CODING_AGENT=true environment variable at startup so subprocesses and scripts can detect they are running inside the coding agent.
›Adds lightweight anonymous install/update telemetry ping to track per-version adoption; controllable via /settings, enableInstallTelemetry in settings.json, PI_OFFLINE=1, or PI_TELEMETRY=0.
Hermes v2026.4.13 adds iMessage/WeChat, Fast Mode, local web dashboard, background process monitoring, backup/restore, and 16-platform coverage.
└──▷ GET THIS VERSION
$ git clone --branch v2026.4.13 https://github.com/NousResearch/hermes-agent.git
# already have the repo? check out this version:$ git checkout v2026.4.13
└──▷ TRY IT
Enable priority-queue routing for low-latency responses when working with GPT-5.4 or Claude in an active session.
$ /fast
Watch a background build or server process and get notified the moment it prints a key event, without polling.
yaml
watch_patterns: ["listening on port", "ERROR", "build failed"]
Snapshot your full Hermes setup before a major upgrade, then restore it on a new machine.
$ hermes backup && hermes import <path>
›Adds local browser-based web dashboard for managing agent settings, sessions, skills, and gateway configuration without editing config files.
›Adds /fast toggle for priority-queue routing on OpenAI (GPT-5.4, Codex) and Anthropic (Claude) models for significantly lower latency.
›Adds iMessage integration via BlueBubbles with auto-webhook registration and setup wizard.
›Adds native WeChat (Weixin) support via iLink Bot API with streaming, media uploads, and markdown link handling.
›Adds WeCom callback-mode adapter for self-built enterprise apps with atomic state persistence.
+17 moreshow less
›Adds Termux/Android support — run Hermes natively on Android with TUI optimizations, voice backend, and /image command.
›Adds watch_patterns for background process monitoring, delivering real-time alerts when output matches defined patterns without polling.
›Adds native xAI (Grok) provider with direct API access, model catalog, and setup wizard integration.
›Adds Xiaomi MiMo as a first-class provider with setup wizard, model catalog, and empty response recovery.
›Adds Qwen OAuth provider with portal request support.
›Adds pluggable context engine slot via hermes plugins for swapping in custom context engines (filtering, summarization, domain injection).
›Adds unified SOCKS proxy, DISCORD_PROXY, and system proxy auto-detection across all gateway platforms.
›Adds hermes backup and hermes import commands for full backup and restore of configuration, sessions, skills, and memory.
›Adds /debug slash command across all platforms and hermes debug share to upload a full debug report to a pastebin.
›Adds /compress <focus> for guided context compression scoped to a specific topic.
›Adds allowed-channels whitelist config for Discord.
›Adds DISCORD_REPLY_TO_MODE setting for Discord.
›Adds rate limit header capture displayed in /usage.
›Adds custom providers to /model listings and resolution.
›Adds fallback provider activation on repeated empty responses with user-visible status.
›Adds comprehensive security hardening: path traversal protection in checkpoint manager, shell injection neutralization in sandbox writes, SSRF redirect guards in Slack image uploads, Twilio webhook signature validation, API server auth enforcement, git argument injection prevention, and approval button authorization.
›Expands platform support to 16 messaging platforms including BlueBubbles (iMessage) and WeChat alongside existing Telegram, Discord, Slack, WhatsApp, Signal, Matrix, Email, SMS, DingTalk, Feishu, WeCom, Mattermost, Home Assistant, and Webhooks.
LangChain Core 1.3.0a2 adds ContextOverflowError, multimodal token counting, XML buffer formatting, and tool-call metadata tracking.
└──▷ GET THIS VERSION
$ git clone --branch langchain-core==1.3.0a2 https://github.com/langchain-ai/langchain.git
# already have the repo? check out this version:$ git checkout langchain-core==1.3.0a2
└──▷ USE IT
Catch context-window overflow explicitly when invoking a model, so you can retry with a shorter prompt instead of handling a generic error.
python
from langchain_core.errors import ContextOverflowError
try:
response = chat_model.invoke(messages)
except ContextOverflowError:
messages = messages[-5:] # trim and retry
response = chat_model.invoke(messages)
Serialize a conversation to XML format for downstream XML-aware processing pipelines.
python
from langchain_core.messages import get_buffer_string, HumanMessage, AIMessage
history = [
HumanMessage(content="What is LangChain?"),
AIMessage(content="A framework for building LLM applications.")
]
xml_output = get_buffer_string(history, format="xml")
print(xml_output)
›Adds 'approximate' alias usable in place of count_tokens_approximately for token estimation.
›Adds count_tokens_approximately support for multimodal messages (images and other non-text content).
›Adds token counting from tool schemas inside count_tokens_approximately.
›Adds ContextOverflowError exception class, raised by Anthropic and OpenAI integrations when context limits are exceeded.
›Adds usage_metadata to LangSmith trace metadata via LangChainTracer.
+12 moreshow less
›Adds tool_call_count field to automatically count and store tool-call metadata in run outputs.
›Adds XML format option for get_buffer_string() message serialization.
›Adds separator parameter to get_buffer_string() to support custom message separators.
›Adds text_inputs and text_outputs fields to model profiles.
›Adds ChatBaseten to the serializable mapping for LangChain serialization support.
›Adds PEP 702 __deprecated__ attribute support to the @deprecated decorator.
›Adds LangSmith integration metadata to create_agent and init_chat_model.
›Adds hardened anti-SSRF protections to core HTTP utilities.
›Adds more file extensions to the ignore list in HTML link extraction utilities.
›Adds tool_call_id to on_tool_error event data for improved callback tracing.
›Adds scaling by reported usage when counting tokens approximately.
›Adds langchain-openrouter as a new provider package.
OpenClaw v2026.4.12 adds Active Memory sub-agent, LM Studio & Codex providers, MLX speech, exec-policy CLI, and Matrix live markers.
└──▷ GET THIS VERSION
$ git clone --branch v2026.4.12 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:$ git checkout v2026.4.12
└──▷ TRY IT
Inspect or lock down which exec tools are approved locally — useful before deploying to a shared or locked-down environment.
$ openclaw exec-policy show
openclaw exec-policy preset strict
openclaw exec-policy set tools.exec.shell false
Run a QA scenario suite inside a throwaway Linux VM so tests cannot pollute your host and results are written back automatically.
$ openclaw qa suite --runner multipass
›New Active Memory plugin runs a dedicated memory sub-agent before each reply, auto-surfacing relevant preferences and past context with configurable message/recent/full context modes, live /verbose inspection, and opt-in transcript persistence.
›New bundled LM Studio provider supports onboarding, runtime model discovery, stream preload, and memory-search embeddings for local/self-hosted OpenAI-compatible models.
›New bundled Codex provider routes codex/gpt-* models through Codex-managed auth, native threads, model discovery, and compaction while keeping openai/gpt-* on the standard OpenAI path.
›New openclaw exec-policy command with show, preset, and set subcommands for synchronizing tools.exec.* config with the local exec approvals file.
›New commands.list RPC on the Gateway lets remote clients discover runtime-native, text, skill, and plugin commands with surface-aware naming and serialized argument metadata.
+6 moreshow less
›New per-provider models.providers.*.request.allowPrivateNetwork setting enables trusted self-hosted OpenAI-compatible endpoints without broadening global network policy.
›New --runner multipass lane for openclaw qa suite runs repo-backed QA scenarios inside a disposable Linux VM and writes back report, summary, and VM logs.
›New openclaw qa credentials admin commands and Convex-backed pooled Telegram credential leasing for lab/QA environments.
›New openclaw qa telegram lane adds live private-group bot-to-bot checks with hardened artifact handling and native Telegram command reply threading.
›Experimental local MLX speech provider for Talk Mode on macOS with explicit provider selection, local utterance playback, interruption handling, and system-voice fallback.
›Matrix integration now adds MSC4357 live markers to draft preview sends and edits so supporting clients can render a typewriter animation that stops when the final edit lands.
THE AI TOOLCHAIN