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 -064, June 16, 2026

THE AI TOOLCHAIN NO. -064
Tail
THE DAILY RELEASE FIREHOSE
PUBLISHED JUNE 16, 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

GitHub Copilot CLI

Sources Release notes → v1.0.63 NOTES

Copilot CLI v1.0.63 adds deferTools MCP config, alphabetic --help sorting, per-session agent mode, and an experimental /rewind overhaul.

└──▷ GET THIS VERSION
$ git clone --branch v1.0.63 https://github.com/github/copilot-cli.git
# already have the repo? check out this version:
$ git checkout v1.0.63
└──▷ USE IT
Keep an MCP server's tools always available in the palette even when tool search is active, so specialised tools are never pruned from context.
json
{
  "mcpServers": {
    "my-server": {
      "command": "npx",
      "args": ["my-mcp-server"],
      "deferTools": true
    }
  }
}
  • Adds deferTools option to MCP server config to keep a server's tools always available even when tool search is enabled.
  • PostToolUse hook matchers (e.g. Edit|Write) are now honored so formatters and linters run only after the tools they target.
  • Options in --help output now sort alphabetically, including options with two long flags.
  • Press w in /diff to hide whitespace-only changes.
  • Blocked image attachments now explain actionable next steps: enable vision via the 'Editor preview features' policy, switch to a vision-capable model, or try a different image.
+9 moreshow less
  • Auth validation errors (e.g. VPN or IP allowlist failures) are shown in the sign-in banner with guidance to check network access.
  • Shows fork-based pull requests in /pr and the branch PR badge.
  • Shows the spill file path when read_bash output is too large.
  • Includes recent local sessions in /chronicle standup.
  • Agent mode is tracked per session and no longer carries over when you create, clear, or switch sessions.
  • Pressing Enter opens the highlighted issue details.
  • Plan review menus work on strict OpenAI-compatible backends.
  • Retries transient 401 auth failures in HMAC and OAuth modes.
  • Resumes remote sessions when the local and remote repository names differ only by case.
Was this useful?

Earendil Works Pi

Sources Release notes → v0.79.5 NOTES

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

Pi v0.79.5 adds provider-scoped API key env overrides, a global HTTP proxy setting, and Vercel AI Gateway attribution headers.

└──▷ GET THIS VERSION
$ git clone --branch v0.79.5 https://github.com/earendil-works/pi.git
# already have the repo? check out this version:
$ git checkout v0.79.5
└──▷ USE IT
Route all Pi AI provider traffic through a corporate proxy without setting shell environment variables.
json
# In Pi global settings (e.g. ~/.config/pi/settings.json)
{
  "httpProxy": "http://proxy.corp.example.com:8080"
}
Scope Bedrock credentials and a custom endpoint to Pi only, keeping your shell environment clean.
json
# In auth.json
{
  "apiKeys": [
    {
      "provider": "amazon-bedrock",
      "env": {
        "AWS_ACCESS_KEY_ID": "AKIA...",
        "AWS_SECRET_ACCESS_KEY": "secret",
        "AWS_REGION": "us-east-1"
      }
    }
  ]
}
  • Adds provider-scoped env overrides in auth.json API key entries for Cloudflare, Azure OpenAI, Google Vertex, Amazon Bedrock, cache retention, and proxy settings — scoped to Pi without touching the project shell.
  • Adds a global httpProxy setting that propagates HTTP_PROXY and HTTPS_PROXY to all Pi-managed HTTP clients.
  • Adds http-referer and x-title attribution headers to Vercel AI Gateway requests by default.
  • Adds an xp footer marker in the UI when experimental features are enabled.
Was this useful?
◆  AI Agent Frameworks

OpenClaw

Sources Release notes → v2026.6.8 NOTES

Your own personal AI assistant. Any OS.

OpenClaw v2026.6.8 adds GLM-5.2 and Claude Haiku 4.5 support, Telegram rich-message delivery, WhatsApp ACP bindings, /btw CLI command, and built-in usage footer rendering.

└──▷ GET THIS VERSION
$ git clone --branch v2026.6.8 https://github.com/openclaw/openclaw.git
# already have the repo? check out this version:
$ git checkout v2026.6.8
  • Adds GLM-5.2 and Claude Haiku 4.5 catalog entries with normalized provider-qualified model IDs across OpenRouter and Google Vertex paths.
  • Adds Telegram rich-message delivery: tables, lists, expandable blockquotes, preserved intentional line breaks, and CLI-backed replies.
  • Adds WhatsApp ACP binding support so configured ACP bindings are honored on delivery.
  • Adds /btw command support in CLI-backed sessions.
  • Adds built-in full footer renderer for /usage and reply payload hooks, including a default footer template, per-turn usage state, credential-aware limits, and fixed-decimal formatting for usage-bar templates.
+1 moreshow less
  • Keeps key-free web search providers (Parallel Free, DuckDuckGo, Ollama, Codex Hosted Search) as explicit opt-ins rather than automatic fallbacks when no API-backed provider is configured.
Was this useful?
◆  Local LLM Runtimes

llama.cpp

Sources Release notes → b9669 3 RELEASES · 2026-06-16 NOTES STABLE

llama.cpp b9669 adds backend sampling support for Eagle3 speculative decoding.

└──▷ GET THIS VERSION
$ git clone --branch b9669 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b9669
  • Adds backend sampling support for Eagle3, enabling hardware-accelerated speculative decoding with the Eagle3 draft model architecture.
2 more releases in this issue · 2026-06-16
b9665 NOTES STABLE

llama.cpp b9665 adds --offline flag to the bench command.

└──▷ GET THIS VERSION
$ git clone --branch b9665 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b9665
└──▷ TRY IT
Run llama.cpp benchmarks in an air-gapped or network-restricted environment without triggering remote calls.
$ llama-bench --offline
  • Adds --offline flag to bench to run benchmarks without network access, with a default value included.
b9664 NOTES STABLE

SYCL backend gains reordered Q4_K, Q5_K, and Q6_K MoE MUL_MAT_ID support for fused expert inference

└──▷ GET THIS VERSION
$ git clone --branch b9664 https://github.com/ggml-org/llama.cpp.git
# already have the repo? check out this version:
$ git checkout b9664
  • Extends SYCL reordered-weight handling to fused MoE MUL_MAT_ID operations for Q4_K, Q5_K, and Q6_K expert tensors, enabling GPU-accelerated MoE inference with these quantization types on SYCL backends.
  • Adds Q5_K reordered DMMV (dequantize matrix-vector multiply) coverage on SYCL.
  • Unsupported 3D reorder cases now fall back gracefully instead of aborting.
Was this useful?
Other / Uncategorized
◆  AI OBSERVABILITY

Arize Phoenix

Sources Release notes → arize-phoenix-v17.7.0 NOTES

Phoenix 17.7.0 adds token detail metrics charts, agent session context, and shareable trace time range URLs.

└──▷ GET THIS VERSION
$ git clone --branch arize-phoenix-v17.7.0 https://github.com/Arize-ai/phoenix.git
# already have the repo? check out this version:
$ git checkout arize-phoenix-v17.7.0
  • Adds token detail metrics charts to visualize granular token usage breakdowns in the UI.
  • Adds session context for agents, enabling richer tracking of agent sessions across traces.
  • Makes trace time range URLs shareable so practitioners can link directly to a specific time window in a trace view.
Was this useful?

Langfuse

Sources Release notes → v3.187.0 NOTES

Langfuse v3.187.0 adds evaluator deletion via UI/API/MCP, reapply-after-delete support, and resource URLs in agent/MCP context.

└──▷ GET THIS VERSION
$ git clone --branch v3.187.0 https://github.com/langfuse/langfuse.git
# already have the repo? check out this version:
$ git checkout v3.187.0
  • Adds ability to delete evaluators through the UI, API, and MCP interfaces.
  • Supports re-applying evaluator deletion, enabling recovery workflows after an evaluator is removed.
  • Includes resource URLs in agent and MCP context for richer tracing of tool calls.
  • Allows the agent window to be resized and repositioned in the UI.
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 →