You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit 9b5bf70
Browse filesBrowse the repository at this point in the historyBrowse files
if printf '%s\n' "$FILES" | grep -qE '^(src/|internal/|install\.(sh|ps1)|scripts/build\.sh|scripts/smoke-test\.sh|scripts/smoke-local\.sh|scripts/smoke-fixture-server\.py|scripts/gen-third-party-notices\.sh|scripts/env\.sh|test-infrastructure/vm/(vm-smoke\.sh|windows-user-path-guard\.ps1)|Makefile\.cbm)'; then
85
+
# A here-string, not a pipe: under this shell's pipefail, grep -q
86
+
# exits on its first match, printf dies of SIGPIPE once the list
87
+
# outgrows the pipe buffer, and the MATCH is then reported as a
88
+
# failure -- product=false, smoke skipped, on the largest PRs.
89
+
if grep -qE '^(src/|internal/|install\.(sh|ps1)|scripts/build\.sh|scripts/smoke-test\.sh|scripts/smoke-local\.sh|scripts/smoke-fixture-server\.py|scripts/gen-third-party-notices\.sh|scripts/env\.sh|test-infrastructure/vm/(vm-smoke\.sh|windows-user-path-guard\.ps1)|Makefile\.cbm)' <<<"$FILES"; then
@@ -149,6 +149,25 @@ If in doubt, open an issue and ask.
149
149
- Run `scripts/test.sh` and `scripts/lint.sh` before submitting
150
150
- Keep PRs focused — avoid unrelated reformatting or refactoring
151
151
152
+
## AI-assisted and AI-authored contributions
153
+
154
+
Contributions written with the help of an AI tool, or written by an AI agent acting for a person, are welcome here on the same terms as any other. What we review is the change, not who or what typed it. Three things make that work:
155
+
156
+
-**Say so.** If an agent wrote the PR or is answering in the thread, disclose it — a line in the PR description or at the top of a comment is enough ("written with X", "this account is operated by an AI agent on behalf of Y"). Disclosure is never held against a contribution. Finding out later is.
157
+
-**A person is accountable.** The [DCO sign-off](#license-and-sign-off-dco--required-on-every-commit) is a legal certification, and only a person can make it. The human behind the account certifies every commit, answers for it, and is who we talk to if something goes wrong. An agent may carry the conversation; it cannot carry the responsibility.
158
+
-**The bar does not move.** Every claim in a PR must be something a reviewer can check: the failing test, the command that was run, the numbers and the machine they came from. "The model says it works" is not evidence, and a confident description does not replace a test that fails without the fix. We read AI-written PRs exactly as carefully as human-written ones — no more suspiciously, and no less.
159
+
160
+
Two practical notes:
161
+
162
+
-`Co-authored-by:` trailers naming a tool are fine. Links to private chat or agent sessions are not — they are dead to everyone else and do not belong in permanent history; we will ask you to remove them.
163
+
- High-volume, low-effort submissions — many near-identical PRs, changes nobody ran, replies that do not engage with the review — will be closed, whoever or whatever produced them. One careful PR is worth more than twenty generated ones.
164
+
165
+
### Who speaks for the project
166
+
167
+
Only the maintainer account ([@DeusData](https://github.com/DeusData)) speaks for this project. A review, an approval, a "this will be merged" or a "this is a duplicate" from any other account is that person's opinion, however official it sounds — helpful reviews from the community are very welcome, and that is what they are.
168
+
169
+
**Impersonating a maintainer is not acceptable**, by a person or by an agent: presenting yourself as part of the maintainer team, posting approvals or change requests styled as maintainer decisions, or telling other contributors what the project has decided. We dismiss such reviews, hide the comments, say publicly in the affected threads that they were not ours, and report and block the account. If you are unsure whether a response you received is from the project, check the account name — and ask.
Copy file name to clipboardExpand all lines: README.md
+7-4Lines changed: 7 additions & 4 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -16,7 +16,7 @@
16
16
17
17
**The fastest and most efficient code intelligence engine for AI coding agents.** Full-indexes an average repository in milliseconds, the Linux kernel (28M LOC, 75K files) in 3 minutes. Answers structural queries in under 1ms. Ships as a native executable with a small verified runtime-asset set for macOS, Linux, and Windows — download, run `install`, done.
18
18
19
-
High-quality parsing through [tree-sitter](https://tree-sitter.github.io/tree-sitter/) AST analysis across all 162 languages, enhanced with [**Hybrid LSP** semantic type resolution](#hybrid-lsp) for Python, TypeScript / JavaScript / JSX / TSX, PHP, C#, Go, C, C++, Java, Kotlin, Rust, and Perl — producing a persistent knowledge graph of functions, classes, call chains, HTTP routes, and cross-service links. 15 MCP tools. No language runtime, hosted service, or API key. Plug and play across 45 supported automatic/conditional client surfaces.
19
+
High-quality parsing through [tree-sitter](https://tree-sitter.github.io/tree-sitter/) AST analysis across all 162 languages, enhanced with [**Hybrid LSP** semantic type resolution](#hybrid-lsp) for Python, TypeScript / JavaScript / JSX / TSX, PHP, C#, Go, C, C++, Java, Kotlin, Rust, and Perl — producing a persistent knowledge graph of functions, classes, call chains, HTTP routes, and cross-service links. 17 MCP tools. No language runtime, hosted service, or API key. Plug and play across 45 supported automatic/conditional client surfaces.
20
20
21
21
> **Research** — The design and benchmarks behind this project are described in the preprint [*Codebase-Memory: Tree-Sitter-Based Knowledge Graphs for LLM Code Exploration via MCP*](https://arxiv.org/abs/2603.27277) (arXiv:2603.27277). Evaluated across 31 real-world repositories: 83% answer quality, 10× fewer tokens, 2.1× fewer tool calls vs. file-by-file exploration.
22
22
@@ -37,7 +37,7 @@ High-quality parsing through [tree-sitter](https://tree-sitter.github.io/tree-si
37
37
-**45 supported automatic/conditional client surfaces** — `install` configures detected clients and safely activates conditional clients only when their documented platform, marker, or explicit existing config path is present. See [Multi-Agent Support](#multi-agent-support) for the complete matrix and manual/UI-only boundaries.
38
38
-**Built-in graph visualization** — 3D interactive UI at `localhost:9749`, served from the binary itself.
39
39
-**Infrastructure-as-code indexing** — Dockerfiles, Kubernetes manifests, and Kustomize overlays indexed as graph nodes with cross-references. `Resource` nodes for K8s kinds, `Module` nodes for Kustomize overlays with `IMPORTS` edges to referenced resources.
40
-
-**15 MCP tools** — search, trace, architecture, impact analysis, targeted index-coverage checks, Cypher queries, dead code detection, cross-service HTTP linking, ADR management, and more.
40
+
-**17 MCP tools** — search, trace, architecture, impact analysis, targeted index-coverage checks, Cypher queries, dead code detection, cross-service HTTP linking, ADR management, and more.
41
41
42
42
## Quick Start
43
43
@@ -461,7 +461,7 @@ Add to `~/.claude.json` (user scope) or project `.mcp.json`:
461
461
}
462
462
```
463
463
464
-
Restart your agent. Verify with `/mcp` — you should see `codebase-memory-mcp` with 15 tools.
464
+
Restart your agent. Verify with `/mcp` — you should see `codebase-memory-mcp` with 17 tools.
465
465
466
466
</details>
467
467
@@ -673,6 +673,7 @@ JSON arguments can also be piped on stdin, for tools that take arguments. A tool
673
673
|`list_projects`| List all indexed projects with node/edge counts. |
674
674
|`delete_project`| Remove a project and all its graph data. |
675
675
|`index_status`| Check indexing status of a project. |
676
+
|`check_index_coverage`| Check whether exact paths or a scope are indexed and fresh. A clean result means no recorded gap, not proof of completeness. |
676
677
677
678
### Querying
678
679
@@ -683,7 +684,9 @@ JSON arguments can also be piped on stdin, for tools that take arguments. A tool
683
684
|`detect_changes`| Map git diff to affected symbols + blast radius with risk classification. |
|`search_code`| Grep-like text search within indexed project files. |
689
692
|`manage_adr`| CRUD for Architecture Decision Records (`get` reads, `update` replaces the whole document, `set_sections` rewrites only the named sections and leaves every other byte untouched, `sections` lists headings). Query modes do not wait behind a same-project reindex; writes remain serialized. |
@@ -849,7 +852,7 @@ Also supported (not yet benchmarked): Ada, Agda, Apex, Assembly (NASM), Astro, A
849
852
src/
850
853
main.c Entry point (MCP stdio server + CLI + install/update/config)
<p>The optional UI variant adds one verified, content-addressed frontend pack and serves an interactive 3D graph at <code>localhost:9749</code> to explore nodes, edges, and clusters visually.</p>
0 commit comments