CodeSeek
A local code-intelligence CLI that gives coding assistants semantic search and call-graph queries.
Per-dimension scores and reasoning
Evidence shows: CLI requires API token for embedding and reranking, but config stored in user directory, no hardcoded credentials found. Installation downloads binary via npm script, but no verification of download source. MCP integration modifies config files, but uninstall command provided. No malicious behavior found, but least privilege, user confirmation, data flow transparency, sensitive data handling, dependency security, external effects, rollback, and source attribution are only partially satisfied due to lack of detailed documentation and verification.
Evidence shows: README and code structure consistent, command descriptions clear. But relies on external APIs (embedding, reranking) and binary download, no offline mode or degradation strategy. Failure messages not detailed in documentation.
Evidence shows: Targeted at AI coding agents, supports multiple languages and platforms, multiple installation methods. Capability boundaries described in README, but trigger precision (e.g., search query accuracy) not detailed. Environment fit good, but no specific IDE or editor integration mentioned.
Evidence shows: README structure clear, installation notes detailed, command naming stable, examples provided. But known limitations not explicitly listed, version changelog missing, maintenance responsibility unclear. License is MIT, but copyright year 2026 may be inaccurate.
Evidence shows: Output supports JSON for machine readability. Provides search and call graph features, has marginal value. But cost-benefit not analyzed, external API dependency may incur costs.
Evidence shows: README claims consistent with code structure, but no test results or independent verification. Facts and inferences not clearly separated.
- API token stored in config file, ensure file permissions are secure.
- Binary download source not verified, supply chain risk.
- Relies on external APIs, may incur costs and privacy concerns.
- MCP integration modifies config files, handle with caution.
What does this agent do, and when should you use it?
CodeSeek is a Rust-powered code-intelligence CLI designed for Claude Code and Codex CLI workflows. It parses Rust, Python, JavaScript, TypeScript, Go, C/C++, and Java with Tree-sitter, extracting functions, classes, and methods for a call graph. Its local project index combines LanceDB vectors, a Tantivy BM25 index, and a serialized PetCodeGraph under ~/.codeseek/<project_hash>/. Search can combine dense, sparse, and graph retrieval through RRF, then optionally rerank results with Qwen3-Reranker; if embedding or reranking is unavailable, it falls back to graph-based name search. It has no daemon or HTTP server: commands run as standalone processes, while MCP mode uses stdio JSON-RPC.
With codeseek init, CodeSeek reads source files, parses supported languages through Tree-sitter ASTs, and extracts functions, classes, and methods. It batches 20 texts per embedding API request, caches embeddings in SQLite, stores vectors in LanceDB, builds a Tantivy BM25 index, serializes a PetCodeGraph call graph, and uses MD5 hashes to reprocess only changed files. With codeseek search <query>, it obtains a query vector and runs LanceDB ANN dense search, Tantivy BM25 sparse search, and PetCodeGraph graph search; Reciprocal Rank Fusion combines candidates and Qwen3-Reranker-4B can rerank them. The callers, callees, and callgraph commands return upstream and downstream symbol relationships, while codeseek install writes MCP configuration for Claude Code and Codex.
- A Claude Code user exploring a large Rust or TypeScript repository wants to locate relevant functions from a natural-language question.
- An engineer maintaining a Python, Java, or Go service needs to identify a function’s callers and downstream dependencies before changing it.
- A developer working in a mixed-language repository wants one local index of functions, classes, methods, and call relationships.
- A Codex CLI user wants MCP-accessible code search and call-graph tools for the repository currently being worked on.
- A developer who regularly commits code wants post-commit and post-merge hooks to refresh the local index automatically.
What are this agent's strengths and limitations?
- Combines Tree-sitter structural extraction, PetCodeGraph call graphs, LanceDB vector search, and Tantivy BM25 in one local CLI.
- Its retrieval path can fuse dense, sparse, and graph results with RRF, then apply optional Qwen3-Reranker-4B cross-encoder reranking.
- MD5-based incremental updates, SQLite embedding caching, and Git hooks reduce the need for full reindexing after every change.
- It documents native MCP installation for both Claude Code and Codex CLI, including five code-intelligence tools.
- Semantic retrieval requires an embedding API token, model, and base URL, so it depends on network access and has undocumented API-cost implications.
- The documented Qwen3-Reranker-4B stage adds roughly 1–2 seconds to search-time ranking.
- Packaged npm binaries are documented only for macOS arm64/x64 and Linux x64; support for other platforms is not established.
- The documented language scope is limited to seven languages, and the available material does not establish cross-project querying, access controls, or shared team indexes.
How do you install or deploy this agent?
Install with npm: npm install -g codeseek, then run codeseek for the first-run interactive setup. The wizard configures an embedding API token, model, and base URL; the documented example uses an OpenAI-compatible provider and Qwen/Qwen3-Embedding-4B. Homebrew installation is: brew tap CodeBendKit/codeseek [email protected]:CodeBendKit/codeseek.git && brew install codeseek. For a source build, install protoc, then run git clone https://github.com/CodeBendKit/codeseek.git, cd codeseek, and ./build.sh --release.
How do you use this agent?
From the project directory, run codeseek init to build the index. Run codeseek search main --limit 10 for symbol search, or codeseek search 'how the code embedding work' for a natural-language query. Use codeseek callers <symbol>, codeseek callees <symbol>, or codeseek callgraph <symbol> for call relationships; query commands support --json. Run codeseek install to write MCP configuration to ~/.claude.json or ./.mcp.json and ~/.codex/config.toml. Run codeseek install-hooks to install post-commit and post-merge indexing hooks.