This release adds 2 notable features for engineering teams evaluating rollout.
Published 1mo
AI Agents & Assistants
✓ No known CVEs patched
✓ No known CVEs patched in this version
Topics
agent-harness
agent-isolation
agentic
ai-agents
ai-coding
ai-tools
+14 more
aider
claude-code
code-provenance
codex
coding-assistant
cursor
developer-tools
gemini-cli
git
git-worktree
llm-agents
python
vcs
worktree
Summary
AI summaryCLI ait status --all now reports actionable readiness for multiple AI agents.
Full changelog
0.42.0
This release improves multi-agent readiness reporting for repositories that use several AI agent CLIs together.
- Text
ait status --allnow starts with actionable CLI readiness forclaude,codex,aider,gemini, andcursor. - Detailed wrapper, PATH, real-binary, memory, and memory-health checks remain available in indented detail lines.
- JSON status fields are unchanged for automation.
- Missing real agent binaries now prefer install guidance over init guidance.
- README documents same-repo multi-agent collaboration: separate wrappers and adapter identities, shared repo-local
.ait/memory and evidence.
Validation:
.venv/bin/pytest -q-> 250 passed, 8 subtests passed.venv/bin/python -m compileall -q src testsgit diff --check.venv/bin/python -m build.venv/bin/python -m twine check dist/*- Clean wheel smoke for text
ait status --allreadiness output
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About Ait
All releases →Related context
Related tools
Earlier breaking changes
- v0.55.52 Keep the built-in claude-code reviewer pinned to the local claude -p CLI even when repository policy defines a conflicting command override.
Beta — feedback welcome: [email protected]