Toolbox/Coding agents

Codebase context

codebase indexing, repo maps and code search for agents

11 repositories, most starred first
State of the category

Graphify-Labs/graphify Graphify-Labs/graphify is the clear leader, offering a widely adopted, deterministic AST-based repo-wide knowledge graph with EXTRACTED/INFERRED edge labels. Before choosing, decide whether you need that single, local-first graph model or a different tradeoff (repo-embedded docs, hybrid vector/BM25 retrieval, lightweight local search, or richer type/dataflow analyses).

VCS-first context
Teams that need auditability, syncable docs, and the repo itself as the system-of-record prefer tools that persist context and agent outputs as real files alongside source, so knowledge and plans travel in Git rather than a hidden index.
Hybrid retrieval & local search
Large codebases and token-sensitive workflows require hybrid sparse+dense retrieval or extremely lightweight, local-first semantic search to reduce model context and improve recall without moving everything into the model.
Type-aware graphs & workflows
Teams doing refactors, security analysis, or precise impact queries need richer AST+LSP+dataflow graphs and workflow orchestration so answers are relationship-aware instead of just file lists.
Edit-time safety & reproducibility
Engineering teams that must constrain agent edits, bind behavior to the edit site, and reproduce runs favor per-file genomes or repo-held execution plans so automated changes are auditable and safe.
Find your fit

Which one matches your setup?

Answer any of the questions — the shortlist updates as you go. Recommendations come from the capability passports below, nothing else.

Where should reviews happen?
Can code leave your infrastructure?
What matters most?
Model access?
Pick at least one answer to get a shortlist.
Side by side

Comparison matrix

Axes are extracted from each project's docs by our review pipeline; the maturity score is computed from stars, growth and commit activity — not an opinion. Click a column to sort.

Runs inModelsContextCost to run
114.6k +2819/7d
CLICoding-agent pluginIDECIBYOKOpenAIAnthropicGeminiOllama / localFixed providerWhole-repo analysisEdge confidence tagsFully local possibleFree for code (local); optional API key for semantic media/docs
5.5k +498/7d
CLIIDECoding-agent pluginCIBYOKOpenAIAnthropicWhole-repo graphRanking & checksSelf-hostableYour API key; provider billing applies.
12.5k +14/7d
CLIIDECoding-agent pluginBYOKOpenAIWhole-repo retrievalHybrid search + filtersCloud APIs (your keys)Requires OpenAI and Zilliz Cloud (Milvus) API keys.
2.7k +16/7d
CLICoding-agent pluginBYOKOllama / localWhole-repo analysisPath/lang filtersFully local runLocal embeddings free with the 'full' variant; slim/latest uses cloud embeddings and your API key.
5.5k +498/7d
CLICoding-agent pluginIDEBYOKOpenAIAnthropicOllama / localFixed providerWhole-repo analysisMinimal filtersFully local possibleYour API key, per-use
1.2k +10/7d
CLICIAnthropicOpenAIDiff + related filesAuthoritative surfaceFully localFree, local binary
765
CLICoding-agent pluginBYOKWhole-repo indexReranker + RRFCloud APIs (your key)Requires your API key for embedding and reranker calls
213 +1/7d
CLICICoding-agent pluginIDEBYOKWhole-repo analysisConfigurable filtersFully localFree, local (no hosted service)
873 +4/7d
CLICoding-agent pluginBYOKWhole-repo analysisTruncation & tiersSelf-hostableSelf-hosted; external model/API costs apply
458
CLICoding-agent pluginFixed providerWhole-repo analysisQuality rules & validateSelf-hostableFree, local
156
CLICIGitHub ActionIDECoding-agent pluginBYOKDiff + related filesRule IDs + lintFully localFree, open-source
At a glance

Capability profiles

Six axes, 0–5 each. The shape tells you the strategy: a wide hexagon is a generalist, a spike is a specialist. Showing the 8 most established — the rest are in the full catalog.

ContextNoiseCustomPrivacyModelsMaturity

Builds a deterministic, AST-based, repo-wide knowledge graph (no embeddings or vector store) with every edge labeled EXTRACTED or INFERRED.

ContextNoiseCustomPrivacyModelsMaturity

Persists a deterministic, human-readable context graph as markdown files inside the repo (no embeddings or external index), so agents can follow real files and share an up-to-date code understanding via git.

ContextNoiseCustomPrivacyModelsMaturity

An MCP plugin that gives Claude Code whole-repo semantic code search via hybrid BM25 + dense vector retrieval backed by Milvus, reducing tokens compared with loading large directories into the model.

ContextNoiseCustomPrivacyModelsMaturity

AST-based semantic search that is extremely lightweight, agent-friendly (skill/MCP plugin), and can run fully locally with offline embeddings.

ContextNoiseCustomPrivacyModelsMaturity

Writes a readable, linked markdown graph of your code (no embeddings or external index), letting agents use a local, regenerable map rather than re-exploring the repo each run.

ContextNoiseCustomPrivacyModelsMaturity

Makes the repository the default system of record for agent context and durable execution plans, keeping intent, tests, and validation in Git rather than in a hidden workflow database.

ContextNoiseCustomPrivacyModelsMaturity

Native Rust CLI that combines AST-based call-graph analysis with a hybrid dense+sparse+RRF+cross-encoder reranker search pipeline and MCP integration for Claude Code.

ContextNoiseCustomPrivacyModelsMaturity

Provides persisted, repository-level structural analyses and composed agent workflows (plan/review/context) via a local MCP server, beyond editor-focused tools.

All repositories (11)

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphif…

114.6k
+2,8197d
Python
5 mo

Code search MCP for Claude Code. Make entire codebase the context for any coding agent.

12.5k
+147d
TypeScript
1 yr

Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understa…

5.5k
+4987d
TypeScript
2 mo

Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understa…

5.5k
+4987d
TypeScript
2 mo

A super light-weight embedded code search engine CLI (AST based) that just works - improves speed and efficie…

2.7k
+167d
Python
7 mo

Turn any repo into an agent-ready workspace for Claude Code, Codex, Cursor, and other coding agents.

1.2k
+107d
Rust
4 mo

100% Rust implementation of code graphRAG with blazing fast AST+FastML parsing, surrealDB backend and advanced…

873
+47d
Rust
11 mo

Rust-powered code intelligence CLI for AI coding agents. Builds call graphs and hybrid semantic search indexes…

765
Rust
3 mo

Living project docs for coding agents: keep guides, progress logs, change maps, and handoff context updated as…

458
-17d
Python
2 mo

Local-only Go static analysis engine with a built-in MCP server. Gives AI coding agents deterministic structur…

213
+17d
Go
3 mo

Open, MIT context format for AI coding agents: centralized .aigx/ rules + a per-file boundary index that targe…

156
-27d
JavaScript
2 mo
Don't want to self-host?

Hosted alternatives

If running your own reviewer is more ops than you want, these managed services cover the same job.

Sourcegraph

Managed code search and codebase context across your repositories, so agents and developers query a hosted index instead of one you build and keep in sync.

Try Sourcegraph
Greptile

Serves full-codebase context as an API for AI tools: point at your repos and get cross-file understanding hosted rather than running your own code-graph.

Try Greptile
Zilliz Cloud

Managed Milvus from the Zilliz team, the hosted vector store behind many code-context setups, run for you instead of operated alongside your indexer.

Try Zilliz Cloud

More in Coding agents