GeezerVison is showing deusdata.github.io — Codebase Memory — Local Code Intelligence & MCP
Local MCP server · Open source
Understand the whole repository.
Codebase Memory (CBM) is an open-source server for the Model Context Protocol (MCP). Give your AI coding agent a persistent knowledge graph of code, documentation and infrastructure. Search symbols, trace relationships and retrieve source evidence through 17 MCP tools.
Focused graph queries help reduce repeated code reading and token use. See the evidence →
A deployment pathService→Workload→Image→Dockerfile→Program
Relationships come from supported source forms. Dynamic values and unresolved references can leave gaps; PDF extraction requires a text layer and does not perform OCR.
Code intelligence
Ask better questions of your repository.
Give your coding agent structural context through 17 MCP tools. Query the same graph from the CLI and open source evidence whenever a result needs verification.
Find the right starting point
Search by symbol, structure, text or meaning. Combine regex and graph filters, BM25 full-text search, and local semantic search to find relevant code even when the wording differs.
search_graphsearch_codeget_file_outline
Follow actual relationships
Tree-sitter parsing and Hybrid LSP resolution build call and dependency relationships for supported languages. Trace callers, callees, data flow and supported cross-service links; query more complex patterns with Cypher.
Map a diff to affected symbols, investigate the blast radius, compare graph snapshots and inspect related tests. Near-clone and semantic relationships help surface related implementations worth reviewing.
detect_changescompare_graphsSIMILAR_TO
Connect the wider system
Link multiple repositories in the same store. Explore service relationships across HTTP, gRPC, GraphQL, tRPC and supported async patterns, or ingest runtime traces to add observed relationships.
Inspect index status and recorded coverage before making a claim. Coverage diagnostics identify skipped, partial or stale evidence so you can read the relevant source directly. Preserve architecture decisions with ADR management.
Combine static reachability, changed tests and admitted per-test coverage to explain which tests a change reaches. Use the result to focus supported CI runs.
Job selection uses repository-specific path rules. Test narrowing currently supports C/C++ with supported TEST/SUITE-style harnesses or declared equivalents.
Start in shadow mode and validate your harness before enabling gating. This repository narrows its Linux x86_64 PR unit-test leg; release and dry-run workflows retain full execution.
Publish the graph and compatible per-test coverage with test-impact publish.
02
Trace the change
Combine changed tests, static relationships and admitted coverage.
03
Select with reasons
test-impact select explains its selection for a runner that accepts named tests or suites.
↳
Broaden when evidence is insufficient
Missing, stale or incomplete evidence broadens the selection or returns run_all. Static reachability alone never omits a suite.
Agent setup
Context that fits your coding workflow.
The installer configures 46 automatic/conditional client surfaces. MCP connections, instructions, skills, profiles and hooks are installed according to each client's supported capabilities.
01 / CONNECTSet up your clients
Configure supported integrations for clients such as Claude Code, Codex CLI, Gemini CLI, Cursor, Zed and OpenCode.
02 / GUIDEGive agents a working method
Skills and instructions guide graph queries, coverage checks and source verification. Supported custom-agent formats get Scout, Verify and Auditor profiles.
03 / MAINTAIN CONTEXTUse supported hooks
Client-specific lifecycle and read/search hooks help surface relevant graph context. Hook and subagent capabilities differ by client and platform.
See the supported clients and integration boundaries
Detected automatically (40): Claude Code, Codex CLI, Gemini CLI, Zed, OpenCode, Antigravity, Aider, KiloCode, VS Code, Cursor, Windsurf, Augment / Auggie, OpenClaw, Kiro, Junie, Hermes, OpenHands, Cline, Warp, Qwen Code, GitHub Copilot CLI, Factory Droid, Crush, Goose, Mistral Vibe, Grok Build, Qoder CLI, Kimi Code CLI, GitLab Duo CLI, Rovo Dev CLI, Amp, Devin CLI / Local, Tabnine, Amazon Q Developer IDE, CodeBuddy Code CLI, IBM Bob Shell, Pochi, Pi, Oh My Pi (omp), and agentty.
Conditional or explicit (6): Continue / cn, Visual Studio, TRAE, Roo Code, IBM Bob IDE, and Sourcegraph Cody.
These are client surfaces, not a promise of identical MCP, hook or subagent support. For example, Pi receives instructions and a skill; Warp's detected skill installation is counted while its MCP connection remains manual. Other manual, UI, cloud and repository-managed integrations are documented separately.
An optional way to explore the same graph your agent queries. Included in standard native releases, with source navigation, architecture maps and the Galaxy view.
Source navigation with indexed relationships and impact context.
Read code in context
Browse files and symbols, inspect callers and dependencies, and keep the relevant source beside the graph.
See the shape of the system
Explore architecture, system structure and the Galaxy graph. Inspect coverage diagnostics and architecture decisions from the same workspace.
Follow the connectionsExpand relationships and trace a call path.Inspect system structureSee source groups and dependencies.Ask about selected codeCaller and callee answers from the indexed graph.
Lens is served on loopback. Browser AI downloads its optional model after you enable it. Its explanations should be checked against the displayed source.
Install the MCP server and configure your coding agent. The native runtime needs no Docker or language runtime; indexing and graph queries need no API key. Standard releases also include the optional Lens open beta.
TERMINAL · macOS / Linux
# Install the native release and agent integrationscurl -fsSL https://raw.githubusercontent.com/DeusData/codebase-memory-mcp/main/install.sh | bash# Restart your agent, then ask:
"Index this project"
# Optional: open CBM Lens (open beta)codebase-memory-mcp daemon start --open
Source analysis and graph storage run locally. Native releases contain the executable and authenticated release-owned assets, including the Lens frontend and agent integration templates.
Use native packages or the npm, PyPI and Go wrappers. Package wrappers use their respective runtimes. Nix and source builds also offer builds without the UI.
Choose the clients you want to configure, restart them after installation, then build your first index.
Reuse the graph to find relevant symbols, follow relationships and retrieve focused source snippets. Compact, paged results help keep repeated repository exploration out of your agent’s context window.
Our March 2026 preprint reports 10× lower token use and 2.1× fewer tool calls across 31 repositories compared with file-by-file exploration.
These measurements cover the study’s backend workloads from March 2026. See the paper for the evaluation setup and full results.
Choose CBM when your coding agent needs a persistent local graph of code, docs and infrastructure. The MCP server brings structural search, source evidence, agent integrations and experimental test selection into one open-source package. The CLI provides direct access, and CBM Lens adds an optional visual workspace in open beta. Native releases run on macOS, Linux and Windows without Docker or a language runtime. Explore the capabilities and Smart CI’s current scope.
How does Codebase Memory reduce AI token use?
Your agent can query indexed relationships and retrieve the relevant symbols or source snippets instead of repeatedly exploring whole files. Compact results and pagination control how much context each query returns. The benefit depends on the task; explore the published token-use measurements.
Does Codebase Memory send my source code anywhere?
The backend indexes source and stores and queries its graph locally. Your coding agent has its own data-handling settings. Lens can optionally download a browser model after you enable it, with inference on-device. Installers and update checks use the network to obtain releases and assets.
How does the index stay current?
Incremental indexing updates changed files. With auto-watch enabled, an eligible active MCP session can watch an already indexed project. Automatic first indexing is a separate opt-in setting. The local UI daemon is not a promise of a permanent background watcher.
How much language coverage is available?
Bundled tree-sitter grammars cover a broad range of languages and formats. Supported language families also have Hybrid LSP semantic resolution. Extraction depth, type resolution and framework relationships vary; the language support matrix describes the details.
Does Smart CI select tests for every indexed language?
No. Test narrowing currently supports C/C++ family code with supported test-harness conventions or declared equivalents. It requires configuration, admitted coverage and a compatible runner. Missing or incompatible evidence broadens execution or returns run_all. See the Smart CI guide.
How do I verify the release?
Use the signed release artifacts and checksums, and review the release's verification information. The security policy explains artifact verification, antivirus reports and vulnerability reporting.
Is it free and open source?
Yes. Codebase Memory is MIT licensed. Source, release binaries, detailed documentation and contribution guidelines are available on GitHub.
Project updates
What's shipping.
Recent releases from GitHub, with the implementation details and fixes behind each version.
You are visitor 01402503 — GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.
