This release adds 3 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
Affected surfaces
auth
breaking_upgrade
Summary
AI summaryAdds repo-local recall source patterns and lint severity gates while keeping daily workflow zero‑touch.
Full changelog
0.33.0
This release moves memory governance further toward the intended product model: users keep using their AI agent CLI, while ait applies recall governance in the background.
- Adds repo-local recall source allow and block patterns in
.ait/memory-policy.json. - Adds recall lint severity gates so teams can decide whether
warningorinfomemory issues are also blocked from automatic context injection. - Keeps the default daily workflow zero-touch: users do not need to run memory commands to benefit from governance.
- Updates
ait memory policy showto render the active recall governance settings. - Clarifies docs that memory commands are diagnostics, CI, and team guardrails, not daily user steps.
Validation:
.venv/bin/pytest -q-> 242 passed, 4 subtests passed.venv/bin/python -m compileall -q src tests.venv/bin/python -m build.venv/bin/python -m twine check dist/*- Clean wheel smoke for policy source allow/block recall governance
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]