Unified TUI and CLI to index and search your local coding agent session history across 11+ providers (Codex, Claude, Gemini, Cursor, Aider, etc.)
The week focused on expanding search functionality with bounded phrase, prefix, and Boolean archive search now available on the pages layer. In parallel, the team resolved several stability issues: archive restoration now handles schema version mismatches (v20–v21 into v22), indexing memory usage…
Get this in your inbox every Monday →A deterministic 0–100 hygiene score — README, license, CI, tests, docs, and freshness.
Who ships this repo — author concentration and the bus factor across the last 300 mainline commits.
How welcoming this repo is to contributors — issue throughput, close time, responsiveness, and good-first-issue count.
What this project is built on — dependency count by ecosystem, the license mix, and anything worth a legal look before you adopt it.
Whether this project's CI can be trusted — pass rate, run times, flaky runs, and which workflow is the weak link.
Grounded in coding_agent_session_search's README, structure, and recent commits — answers won't invent code they haven't seen.
A Monday email with what shipped, in plain English — no account needed.
Showing raw commit titles for the newest commits. Sign in to generate AI summaries.
chore(beads): review follow-ups on 8fr1g and b7rhs; reporter evidence on 2l1b0.3, 2l1b0.40 and 962e8; v6rd9 message correction (coding_agent_session_search-8fr1g) (coding_agent_session_search-b7rhs)
style: cargo fmt eight files that left main's fmt check red, and collapse one nested if that fails clippy
fix(cli): `cass help serve` and `cass help archive` show their help (coding_agent_session_search-8fr1g)
fix(codebuff): retain partial scans and preserve source diagnostics
perf(index): retain exactly unchanged canonical vector generations without rewriting
test(search): validate exact external-runtime checkpoint and query integration
feat(experiments): retain GH501 admission path, CASS bridge and qualification harness
feat(experiments): retain GH501 local receipt store and native regressions
chore(beads): close b7rhs (GH #511), 8fr1g and v6rd9 on their receipts; A/B evidence on k2k20 and o9ixv; Windows evidence on 2l1b0.74 (coding_agent_session_search-b7rhs) (coding_agent_session_search-8fr1g) (coding_agent_session_search-v6rd9)
A floor, not a guess: counts only commits whose author, co-author trailer, or message explicitly credits an AI tool (Claude, Copilot, Cursor, aider, Codex…). Based on 30 mainline commits. Unattributed AI code isn't counted here — the full audit estimates that separately.
