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 -072, June 8, 2026

THE AI TOOLCHAIN NO. -072
Tail
THE DAILY RELEASE FIREHOSE
PUBLISHED JUNE 8, 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 Coding Agents

Anthropic Claude Code

Sources Release notes → v2.1.169 NOTES

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 v2.1.169 adds --safe-mode, /cd command, and disableBundledSkills for cleaner troubleshooting and session control.

└──▷ GET THIS VERSION
$ git clone --branch v2.1.169 https://github.com/anthropics/claude-code.git
# already have the repo? check out this version:
$ git checkout v2.1.169
└──▷ TRY IT
Troubleshoot a misbehaving setup by launching Claude Code with all customizations stripped out — no CLAUDE.md, hooks, plugins, or MCP servers.
$ claude --safe-mode
Switch your active session to a different project directory without losing prompt cache continuity.
$ /cd ~/projects/other-repo
List all background agent sessions — including completed ones — with their IDs and states for scripting or monitoring pipelines.
$ claude agents --json --all
  • ›Adds --safe-mode flag (and CLAUDE_CODE_SAFE_MODE env var) to launch with all customizations disabled — CLAUDE.md, plugins, skills, hooks, and MCP servers — for clean troubleshooting.
  • ›Adds /cd command to change the working directory mid-session without breaking the prompt cache.
  • ›Adds disableBundledSkills setting and CLAUDE_CODE_DISABLE_BUNDLED_SKILLS env var to hide bundled skills, workflows, and built-in slash commands from the model.
  • ›Adds --all flag to claude agents --json to include completed sessions; also surfaces new id and state fields on each session entry.
  • ›The claude agents --json command now correctly includes blocked and just-dispatched background sessions.
+5 moreshow less
  • ›Background sessions now preserve --ide, --chrome, --bare, --remote-control, and other flags across retire→wake cycles.
  • ›Remote-managed settings with an invalid entry now apply remaining valid policies and surface the validation error instead of silently dropping the whole payload.
  • ›/workflows command now opens immediately even while a turn is in progress.
  • ›The "CLAUDE.md is too long" warning threshold now scales with the model's context window.
  • ›Adds a tip suggesting claude agents when running multiple concurrent sessions.
Was this useful?

OpenAI Codex CLI

Sources Release notes → rust-v0.138.0 NOTES

Lightweight coding agent that runs in your terminal

Codex CLI gains Desktop handoff, richer plugin JSON output, image path exposure, PAT v2 auth, and flexible reasoning effort selection.

└──▷ GET THIS VERSION
$ git clone --branch rust-v0.138.0 https://github.com/openai/codex.git
# already have the repo? check out this version:
$ git checkout rust-v0.138.0
└──▷ TRY IT
Hand off an active CLI session to Codex Desktop on macOS or Windows without losing context.
$ /app
Get structured JSON output from plugin marketplace commands for scripting or CI pipelines.
$ codex plugin list --json
  • ›Adds /app command to hand off the current CLI thread into Codex Desktop on macOS and native Windows, with Windows workspace launches opening directly into Desktop.
  • ›Exposes saved file paths for local image attachments and standalone image generations to the model, enabling more reliable follow-up edits and file references.
  • ›Adds fallback keyboard shortcuts in the TUI for reasoning effort selection on terminals missing Alt bindings, and supports model-defined effort levels in model-advertised order.
  • ›App-server integrations can now read account token usage via the API.
  • ›Adds support for v2 personal access tokens in CLI and app-server authentication flows.
+1 moreshow less
  • ›Adds --json output to plugin add/remove and marketplace commands; plugin list JSON now includes marketplace source; plugin detail data exposes default prompts, remote MCP servers, and unavailable app templates.
Was this useful?

Earendil Works Pi

Sources Release notes → v0.79.0 NOTES

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

Pi v0.79.0 adds project trust gating with --approve controls, extension-driven trust decisions, and cache-hit visibility in the footer.

└──▷ GET THIS VERSION
$ git clone --branch v0.79.0 https://github.com/earendil-works/pi.git
# already have the repo? check out this version:
$ git checkout v0.79.0
└──▷ TRY IT
Run Pi in CI or a script without interactive trust prompts, auto-approving all project-local resources.
$ pi --approve
Run Pi in an environment where you want to block all project-local resources without any prompt.
$ pi --no-approve
  • ›Adds project trust gating: Pi now prompts before loading project-local settings, resources, instructions, and packages, with --approve / --no-approve flags for non-interactive automation.
  • ›Adds project_trust extension event so global and CLI extensions can decide, remember, or defer trust decisions before project-local resources load.
  • ›Adds prompt cache hit rate (CH) display to the interactive footer for real-time cache visibility.
  • ›Exports RPC extension UI request/response types and coding-agent package asset path helpers from the public SDK API.
Was this useful?
◆  AI Agent Frameworks

browser-use

Sources Release notes → 0.13.0 NOTES

browser-use 0.13.0 ships a Rust-backed beta agent via from browser_use.beta import Agent

└──▷ GET THIS VERSION
$ git clone --branch 0.13.0 https://github.com/browser-use/browser-use.git
# already have the repo? check out this version:
$ git checkout 0.13.0
  • ›Adds from browser_use.beta import Agent, a new Rust-backed beta agent that gives modern models a more direct browser control loop, installable via uv add 'browser-use[core]'.
  • ›Adds x402 skill support to the agent.
Was this useful?
◆  Local LLM Runtimes

llama.cpp

Sources Release notes → b9568 3 RELEASES · 2026-06-08 NOTES STABLE

llama.cpp b9568 adds MTP support for Gemma-4 E2B and E4B assistant models.

└──▷ GET THIS VERSION
$ git clone --branch b9568 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b9568
  • ›Adds multi-token prediction (MTP) support for Gemma-4 E2B and E4B assistant model variants, including masked_embd tensors in the gemma4-assist architecture and converter updates to handle masked_embedding tensor filtering during conversion.
2 more releases in this issue · 2026-06-08
b9562 NOTES STABLE

llama.cpp b9562 adds video input support via --video CLI arg, base64 server input, and MTMD_VIDEO config.

└──▷ GET THIS VERSION
$ git clone --branch b9562 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b9562
  • ›Adds --video CLI argument to enable video input for multimodal inference from the command line, with auto-completion support.
  • ›Adds MTMD_VIDEO configuration option to control video input support.
  • ›Supports video input on the server via base64-encoded input payloads.
  • ›Introduces mtmd_helper_video helper for video handling in the multimodal (mtmd) subsystem.
b9556 NOTES STABLE

llama.cpp b9556 adds HIP support for AMD RDNA3.5 GPUs gfx1152 and gfx1153.

└──▷ GET THIS VERSION
$ git clone --branch b9556 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b9556
  • ›Adds gfx1152 and gfx1153 GPU targets to the HIP backend under the RDNA3.5 architecture class, enabling GPU-accelerated inference on those AMD chips.
Was this useful?
Other / Uncategorized
◆  AI OBSERVABILITY

Langfuse

Sources Release notes → v3.179.0 NOTES

Langfuse v3.179.0 adds a v3 Scores API with cursor pagination and polymorphic values, OpenAI Responses API support, and MCP/CLI settings UI.

└──▷ GET THIS VERSION
$ git clone --branch v3.179.0 https://github.com/langfuse/langfuse.git
# already have the repo? check out this version:
$ git checkout v3.179.0
  • ›Adds v3 Scores API with polymorphic value support, cursor pagination, field groups, and full filter params (Phases 1–4), behind a feature flag.
  • ›Adds LANGFUSE_CLICKHOUSE_DELETED_MASK_CLEANER_CLUSTER_MODE_ENABLED environment variable to control cluster-mode deletion mask cleaning for self-hosted deployments.
  • ›Adds V4 self-hosted environment variables for the worker service.
  • ›Supports OpenAI Responses API connections for LLM integrations.
  • ›Adds MCP and CLI settings page and agent tools banner in the web UI.
+4 moreshow less
  • ›Handles numeric columns in getObservationFilterValues for MCP.
  • ›Introduces a deletion mask cleaner for managing data lifecycle.
  • ›Decouples blob-storage export source visibility from the V4 beta toggle.
  • ›Adds charting support in the experiments list view; moves experiments UI tables to general availability.
Was this useful?
// END OF TRANSMISSION

The AI Toolchain · curated daily · June 8, 2026
Releases & features from the open-source and commercial AI tools that practitioners actually run.

▷ Subscribe
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 →