Codebase Memory
Latest release v0.11.0 on 2026-09-15 · Actively maintained · 12 releases in 90 days
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single…
| Latest release | v0.11.0 on 2026-09-15 |
|---|---|
| Maintenance | Actively maintained — pushed within the last 14 days, with 3 or more releases in 90 days |
| Stars | 43,957 |
| Releases in 90 days | 12 |
| Last commit | 2026-09-21 |
| Repository | DeusData/codebase-memory-mcp |
| Licence | MIT |
| Open issues | 598 |
Recent releases
v0.11.0 2026-09-15
What's new
- New languages
- New tooling: a bounded file outline tool and a bounded graph comparison tool,
- New platforms and surfaces: NetBSD support across CLI, daemon IPC and runtime (,
Fixed
- Patch because the index format moves (one rebuild, below) and the tool output contract changes
Faster
- C++ short-name type lookups are indexed rather than scanned, with a
- Follow-up unifying the two short-name indexes
- Coverage finds a line by table lookup instead of rescanning the file, and stops reporting a
- Duplicate range and a line past EOF (,,, closes )
Changed
- Moved behind explicit opt-in: diagnostics, evidence columns, progress chatter, and JSON output
- Renameat on the parent directory handle, so the symlink survives — the target is edited, never
- Replaced. Other-owner links, dangling links, links to directories and world-writable parents…
v0.10.8 2026-08-19
A community-heavy patch release: 19 pull requests merged since v0.10.6, most from contributors. Thank you all! Cypher aggregates no longer undercount…
0.10.7 2026-08-18
Fixed
- Converge Function/Method istest with the tests/ path filter
- Scope pre-commit clang-tidy to staged changes
- Isolate semantic-only JSON search
- Preserve compound requested fields
Maintenance status is derived from public repository activity — release cadence and commit recency. It is not a review, an endorsement, or a security assessment. Star counts measure attention, not quality.