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 v2.1.128 adds ZIP plugin support, channels auth expansion, MCP server diagnostics, and smarter /mcp and /color UX.
└──▷ GET THIS VERSION
$ git clone --branch v2.1.128 https://github.com/anthropics/claude-code.git
# already have the repo? check out this version:$ git checkout v2.1.128
└──▷ TRY IT
Install a plugin distributed as a ZIP archive without unpacking it first.
$ claude --plugin-dir ./my-plugin.zip
Audit connected MCP servers to spot any that registered zero tools (possible misconfiguration).
$ /mcp
›Bare /color with no arguments now picks a random session color.
›Adds tool-count display to /mcp output; servers that connect with zero tools are flagged.
›--plugin-dir now accepts .zip plugin archives in addition to directories.
›--channels now works with console (API key) authentication; console orgs with managed settings must set channelsEnabled: true to enable.
›Updated /model picker collapses duplicate Opus 4.7 entries and labels the current Opus model simply as "Opus".
+5 moreshow less
›Subprocesses (Bash, hooks, MCP, LSP) no longer inherit OTEL_* environment variables, isolating OTEL-instrumented apps from the CLI's own OTLP endpoint.
›Reconnecting MCP servers now summarize re-announced tools by server prefix instead of flooding the conversation with full tool-name lists.
›SDK hosts now receive a persistent localSettings suggestion for Bash permission prompts, so "Always allow" writes to .claude/settings.local.json.
›Auto mode classifier errors now include a hint (retry, /compact, or run with --debug) when an action cannot be evaluated.
›Headless --output-format stream-json: init.plugin_errors now includes --plugin-dir load failures in addition to dependency demotions.
└──▷ BREAKING ON UPGRADE
!workspace is now a reserved MCP server name — existing servers configured with that name will be skipped with a warning.
!Subprocesses (Bash, hooks, MCP, LSP) no longer inherit OTEL_* environment variables; any setup relying on subprocess inheritance of the CLI's OTEL config will stop working.
!EnterWorktree now creates the new branch from local HEAD instead of origin/<default-branch>; workflows that depended on the previous behavior of branching from the remote default may behave differently.
Pi v0.73.0 adds incremental bash streaming, compact read rendering, and Xiaomi MiMo API billing with regional Token Plan providers.
└──▷ GET THIS VERSION
$ git clone --branch v0.73.0 https://github.com/earendil-works/pi.git
# already have the repo? check out this version:$ git checkout v0.73.0
›Adds Xiaomi MiMo API billing provider (xiaomi) alongside three regional Token Plan providers: xiaomi-token-plan-cn, xiaomi-token-plan-ams, and xiaomi-token-plan-sgp, each defaulting to mimo-v2.5-pro.
›Streams bash tool output incrementally as commands run, rather than buffering until completion.
›Collapses Pi docs, AGENTS/CLAUDE context files, and SKILL.md contents by default in interactive read output, showing only selected line ranges.
└──▷ BREAKING ON UPGRADE
!The built-in xiaomi provider now uses Xiaomi's API billing endpoint instead of Token Plan AMS; XIAOMI_API_KEY must now be an API billing key from platform.xiaomimimo.com. Users on Token Plan must switch to xiaomi-token-plan-cn, xiaomi-token-plan-ams, or xiaomi-token-plan-sgp and set the corresponding env var (XIAOMI_TOKEN_PLAN_CN_API_KEY, XIAOMI_TOKEN_PLAN_AMS_API_KEY, or XIAOMI_TOKEN_PLAN_SGP_API_KEY).
!The /login display name for the built-in Xiaomi provider is renamed from "Xiaomi MiMo Token Plan" to "Xiaomi MiMo".
langgraph-checkpoint-postgres 3.1.0a4 exposes a public get_writes_history saver API with reworked delta cadence.
└──▷ GET THIS VERSION
$ git clone --branch checkpointpostgres==3.1.0a4 https://github.com/langchain-ai/langgraph.git
# already have the repo? check out this version:$ git checkout checkpointpostgres==3.1.0a4
└──▷ USE IT
Retrieve the full write history for a thread to audit or replay state transitions stored in Postgres.
python
history = await saver.get_writes_history(config)
›Adds public get_writes_history API on the checkpoint saver, enabling programmatic retrieval of write history for a thread.
›Reworks delta cadence logic for checkpoint writes, enabling finer-grained control over how incremental state changes are persisted.
OpenClaw v2026.5.3 adds a bundled file-transfer plugin, /steer command, WhatsApp Newsletter targets, and unified streaming progress drafts.
└──▷ GET THIS VERSION
$ git clone --branch v2026.5.3 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:$ git checkout v2026.5.3
└──▷ TRY IT
Steer a running agent session mid-flight without queuing a new turn — useful when you want to redirect the active run interactively.
$ /steer focus only on the authentication module and skip the database layer
Inspect installed plugins and their npm dependency state to audit which packages are fully resolved vs. broken.
$ openclaw plugins list --json
›Adds bundled file-transfer plugin with file_fetch, dir_list, dir_fetch, and file_write agent tools for binary file operations on paired nodes, with default-deny per-node path policy, symlink traversal off by default (opt-in followSymlinks), and a 16 MB per-round-trip ceiling.
›Adds /steer <message> command for queue-independent steering of the active current-session run without starting a new turn when the session is idle.
›Adds /side as a text and native slash-command alias for /btw side questions.
›Adds unified streaming.mode: "progress" drafts with auto single-word status labels and shared progress configuration across Discord, Telegram, Matrix, Slack, and Microsoft Teams.
›Supports explicit WhatsApp Channel/Newsletter @newsletter outbound message targets with channel session metadata instead of DM routing.
+9 moreshow less
›Adds trackToolCalls: true option on explicit Discord reaction tool calls to opt into tracking subsequent tool progress on the reacted message.
›Adds tree-sitter-backed shell command explainer for approval and command-review surfaces.
›Includes package dependency install state in openclaw plugins list --json output.
›Annotates ClawHub 429 errors with reset windows and unauthenticated higher-rate-limit hints so operators can tell when downloads recover and when signing in helps.
›Stores sandbox container and browser registry entries as per-runtime shard files, reducing unrelated session lock contention.
›Adds pnpm openclaw qa mantis discord-smoke runner and manual GitHub workflow to verify Mantis Discord bot connectivity, smoke posting, reactions, and artifact upload.
›Adds a Slack live transport QA runner with canary and mention-gating coverage.
›Exposes the external Codex plugin as a selectable provider setup choice in Manual setup onboarding.
›Tries plugin @beta updates first on the beta OpenClaw channel, falling back to default/latest when no plugin beta release exists.
└──▷ BREAKING ON UPGRADE
!Gateway startup and hot reload no longer auto-restore invalid config; invalid config now fails closed and requires openclaw doctor --fix to repair.
llama.cpp b9018 adds a built-in get_datetime server tool for time-aware LLM interactions.
└──▷ GET THIS VERSION
$ git clone --branch b9018 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:$ git checkout b9018
›Adds get_datetime as a built-in server tool, giving the llama.cpp server a native way to expose current date/time to the model without custom tool implementations.
THE AI TOOLCHAIN