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 -293, October 28, 2025

THE AI TOOLCHAIN NO. -293
Tail
THE DAILY RELEASE FIREHOSE
PUBLISHED OCTOBER 28, 2025 · 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   # 5 tools matched
AI & LLM Tooling
◆  AI Coding Agents

GitHub Copilot CLI

Sources Release notes → v0.0.353 NOTES

GitHub Copilot CLI v0.0.353 adds custom agents and async task delegation via /delegate.

└──▷ GET THIS VERSION
$ git clone --branch v0.0.353 https://github.com/github/copilot-cli.git
# already have the repo? check out this version:
$ git checkout v0.0.353
└──▷ TRY IT
Invoke a named custom agent noninteractively to run a scoped task without entering the interactive prompt.
$ gh copilot suggest --agent security-reviewer 'Review this PR for injection vulnerabilities'
Hand off a long-running remediation task to Copilot in the background while you continue other work — Copilot opens a PR and completes the changes asynchronously.
$ /delegate Fix all TODO comments in the authentication module
  • Adds --agent <agent> flag (noninteractive) and /agent slash command (interactive) to explicitly invoke custom agents; agent definitions are loaded from ~/.copilot/agents, .github/agents in the current repo, or the organization's .github repository.
  • Adds /delegate slash command to asynchronously hand off a task to the Copilot coding agent — unstaged changes are committed to a new branch, a PR is opened, and Copilot completes the work in the background.
Was this useful?

SST OpenCode

Sources Release notes → v0.15.19 NOTES

The open source coding agent.

OpenCode v0.15.19 adds ACP MCP server support, file diffs, default slash commands, and a new session.started event.

└──▷ GET THIS VERSION
$ git clone --branch v0.15.19 https://github.com/sst/opencode.git
# already have the repo? check out this version:
$ git checkout v0.15.19
└──▷ TRY IT
Test VCS-dependent behaviour in a controlled environment without a real git repo.
$ OPENCODE_FAKE_VCS=1 opencode
  • Adds MCP server support, file diffs, and default slash commands (/init, /compact) in ACP.
  • Adds session.started event that triggers when a new session is created.
  • Adds OPENCODE_FAKE_VCS flag for VCS testing.
Was this useful?
◆  AI Agent Frameworks

PydanticAI

Sources Release notes → v1.7.0 NOTES

PydanticAI v1.7.0 adds OutlinesModel for running local LLMs via Transformers, Llama.cpp, MLXLM, SGLang, and vLLM

└──▷ GET THIS VERSION
$ git clone --branch v1.7.0 https://github.com/pydantic/pydantic-ai.git
# already have the repo? check out this version:
$ git checkout v1.7.0
└──▷ USE IT
Run a structured-output agent against a local model without any cloud API keys, using the Transformers backend via Outlines.
python
from pydantic_ai import Agent
from pydantic_ai.models.outlines import OutlinesModel

model = OutlinesModel('transformers', model_name='mistralai/Mistral-7B-v0.1')
agent = Agent(model)
result = agent.run_sync('Summarize this CVE advisory: ...')
print(result.data)
  • Adds OutlinesModel class to run local models through the Outlines library, supporting Transformers, Llama.cpp, MLXLM, SGLang, and vLLM backends.
Was this useful?

browser-use

Sources Release notes → 0.9.3 2 RELEASES · 2025-10-28 NOTES STABLE

browser-use 0.9.3 adds a template generation command for quick project setup and switches install to uvx browser-use install.

└──▷ GET THIS VERSION
$ git clone --branch 0.9.3 https://github.com/browser-use/browser-use.git
# already have the repo? check out this version:
$ git checkout 0.9.3
  • Changes the browser-use install invocation to uvx browser-use install.
  • Adds a template generation command for quick project scaffolding.
└──▷ BREAKING ON UPGRADE
  • !The browser-use install command has changed: users must now run uvx browser-use install instead of the previous invocation.
1 more release in this issue · 2025-10-28
0.9.2 NOTES STABLE

browser-use 0.9.2 adds direct action call API via __getattr__, element lookup helpers on BrowserSession, and a new uvx browser-use install command.

└──▷ GET THIS VERSION
$ git clone --branch 0.9.2 https://github.com/browser-use/browser-use.git
# already have the repo? check out this version:
$ git checkout 0.9.2
└──▷ TRY IT
Install browser-use without a pre-existing project setup, useful for one-off automation or CI bootstrapping.
$ uvx browser-use install
  • Adds uvx browser-use install subcommand for quick installation via uvx.
  • Adds direct action call API to Tools via __getattr__, enabling actions to be invoked as methods directly on the Tools object.
  • Adds element lookup helper methods to BrowserSession for programmatic element access.
  • Expands code-use exports to include JavaScript code blocks alongside existing output formats.
Was this useful?
Other / Uncategorized
◆  AI OBSERVABILITY

Langfuse

Sources Release notes → v3.123.0 NOTES

Langfuse v3.123.0 adds chunked historic blob exports and opt-in OpenTelemetry performance improvements for self-hosters.

└──▷ GET THIS VERSION
$ git clone --branch v3.123.0 https://github.com/langfuse/langfuse.git
# already have the repo? check out this version:
$ git checkout v3.123.0
  • Adds opt-in performance improvements for self-hosters using OpenTelemetry SDKs.
  • Implements chunked historic exports for blob/object-store export jobs, enabling reliable large-scale data exports.
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 →