Codebase graph analysis for AI agents — AST + call graph + type graph + hybrid semantic search via MCP

Codebase graph analysis for AI agents — AST + call graph + type graph + hybrid semantic search via MCP

Manage, analyze, and visualize knowledge graphs with support for multiple graph types including topologies, timelines, and ontologies. Seamlessly integrate with MCP-compatible AI assistants to query and manipulate knowledge graph data. Benefit from comprehensive resource management and version status tracking to enhance your knowledge workflows.

Local personal knowledge graph: plain-English facts → typed graph → context snapshot for any AI chat. Ollama, SQLite, MCP server. Paused; experiment write-up inside.

The call graph from your compiler or type checker, for humans and coding agents

Local-first, graph-linked persistent memory for AI coding agents — MCP server + CLI. SQLite knowledge graph, typed edges, 4-band dedup, once-per-session briefings, no telemetry.

Zero-dependency repo-indexing engine: deterministic walk + symbol/import extraction (tree-sitter AST with regex fallback) + typed cross-file link-graph + analytics. One vendorable engine.mjs, CLI + MCP server included.

A typed, provenance-aware knowledge graph over an Obsidian vault, exposed to coding agents over MCP. Zero third-party runtime dependencies.

AI memory as a typed knowledge graph in Obsidian. Like Mem0, but you own your data.

MCP memory server: SQLite slot-facts + lossless log, FTS/vectors/graph recall, typed links, atomic batch.

Local-first markdown memory system for humans and AI agents: MCP server, typed knowledge graph, deterministic garden planning.

Ontara: local-first worldbuilding app for authors. Model fictional universes as a typed graph of entities and events.

Local knowledge graph for agents: typed relationships, source-linked retrieval, budgeted context packs, and Python, HTTP and MCP interfaces.

Guild knowledge graph for AI agents: MCP server (59 tools: search, post, typed links, comments, guilds) + Agent Skill + Claude Code plugin. MIT.

Knowledge Vault MCP Server — structured wiki with BM25 search, typed knowledge graph, batch validation, and companion skills for autonomous knowledge compilation.

Semantic Scholar MCP server: 14 typed tools for paper search, citation graphs, author profiles, recommendations, PyPI/Docker.

MCP server to search and inspect Substreams packages — browse the registry and introspect .spkg module graphs, protobuf types, and DAG dependencies

MCP server that gives AI agents semantic search tool. Builds AST, call graphs, type graphs, and hybrid semantic search — so your agent queries structured indexes instead of dumping files into context. 7 languages. Zero config. One command setup.

Code map & call-graph MCP server for AI agents. Tree-sitter + SQLite index of PHP/Go/TS code with type-inference enrichment — semantic search, callers, implementations in milliseconds.

A code graph an LLM can actually use. Tree-sitter across 6 languages, typed ontology with inferred architectural roles, impact analysis, 9 interactive views, MCP server. No embeddings, no vector DB.

Knowledge graph memory for Claude Code and Codex CLI — persistent nodes, typed edges, recall at the moment it applies, self-maintaining. One local memory both agents share.

Local MCP server for read-only C# code navigation and .NET assembly inspection. Roslyn symbol search, call graphs, references, type hierarchies, and ILSpy decompilation for AI coding agents.

MCP server giving LLM agents access to databases, files, graphs, and a full data science toolkit — 52 tools across 13 database types and 20+ file formats

Personal Knowledge Brain for developers — MCP server with typed neurons, hybrid search (FTS5 + vector), knowledge graph, vault encryption, time-travel history, and spaced repetition. 100% local, SQLite-based.

Native repository intelligence for coding agents: 66 MCP operations backed by typed evidence graphs, impact, architecture, local CI restrictions, APIs, Git, search, semantic links, n8n workflows, Dify apps, agent packages, Mermaid diagrams, and Web3 ABIs.

Read huggingface.co as data: every model, dataset, space, user, org, collection and paper as a typed record with an hf:// URI and a knowledge graph of the edges between them

Read github.com as data: every repo, user, org, issue, pull request, commit, release and file as a typed record with a github:// URI and a knowledge graph of the edges between them, with no API token

Long-term memory for AI agents as an MCP server: typed records searched by meaning and a directed knowledge graph between projects. SQLite with sqlite-vec or PostgreSQL, in-process ONNX embeddings, one local HTTP server for every session.

Agent memory you can code-review. Tusk indexes a folder of markdown into a typed, searchable graph your agents query over MCP. It stays plain files in git, and tusk doctor fails CI when a link dangles or a convention breaks.

A Claude Code plugin that turns AI-assisted work into a shared living ontology. Captures decisions, conventions, and context autonomously into typed, interlinked knowledge nodes (git-committed markdown). Navigate the ontology as a graph, trace conceptual paths between ideas, and catch doc-code drift before every commit.

An MCP server giving AI agents associative memory, modelled on the human mind. The name comes from engraphy, the old memory-science term for laying down an engram, the trace a memory leaves in the brain. Self-hosted: typed graph on Postgres and pgvector. Source-available under BSL 1.1.

Knowledge engine for AI agents: your documents become a git-versioned markdown knowledge graph the agent navigates over MCP. Curated summaries, typed edges, cited answers, SQL over your spreadsheets, no chunking. Same 12B local model: 0/11 on multi-hop questions as top-k RAG, 11/11 as a navigator. Python, Apache-2.0, self-hostable.

Open-source Software Intelligence Platform. Deterministic verification, structural PR reviews, interactive graph explorer, and proactive intelligence — powered by the Software Graph. 41 node types · 32 relationships · 120+ checks.

MCP tools for code generation from compact JSON recipes, type graphs, and OpenAPI, GraphQL, Protobuf, or SQL schemas. Generate linked types and custom code with imports across 11 languages.

Store, search, and retrieve memories with semantic and keyword search. Create relationships between memories to build knowledge graphs. Organize with tags, types, and trust levels. Publish memories to shared spaces and manage user preferences for intelligent context retention.

MCP server giving AI agents persistent memory: Markdown files as source of truth, hybrid BM25 + embedding search, typed graph relations. Self-hosted, single Docker image.

Cognitive memory for AI agents. MCP server with 5 memory types, composite weight scoring, and a knowledge graph. SQLite as source of truth, Obsidian as the view layer. Embeddings run locally, no API keys.

Claude Code plugin for Synapse, a compiler for AI agent workflows: compiles a workflow to a typed graph, optimizes it, and blocks any rewrite that fails an equivalence check. Side-effecting steps are never reordered, repeated or cached. MCP server + 4 slash commands.

The orchestration layer under your coding agent. Turns work into a typed graph, runs one model per node, and takes the verdict from outside the model — exit codes, write-set checks, and a cross-family verifier. MCP server, 50 tools, bring your own models.

AI agent pipeline orchestration for Claude Code. Deploy specialized agents in coordinated pipelines with self-learning capabilities, mesh coordination, Raft consensus, CRDT knowledge graphs, and pipeline debugging. 15 production-grade skills with reasoning protocols, 20+ agent types, 15 ready-to-run templates. Zero infrastructure.

A command-line tool for analyzing and visualizing type dependencies in C# assemblies. Works as both a CLI tool and an MCP (Model Context Protocol) server for AI agents.

A Cloudflare Worker (with Durable Objects) MCP server for a single Microsoft To Do account. Keeps a synced SQLite copy of your lists and tasks for fast, large queries via delta sync. Configurable list-type classification and per-list sync exclusions (flaggedEmails skipped by default).

Typed catalog of cognitive primitives, cross-referenced and lineage-grounded, with a surfacing function on top.

LLM-first Three.js WebGPU scene and animation authoring with a persistent native viewport and typed MCP editing

Self-hosted AI agent memory server with MCP, evidence provenance, typed claims, conflict detection, embeddings, recall, PostgreSQL, and pgvector

MCP server for StackMap - the curated map of the open-source AI stack. Every connection typed and human-reviewed, with the why written down.

Native MCP for coding agents: 43 read-only repository-intelligence tools with typed evidence, impact, architecture, APIs, Git, search, semantics, and memory.

MCP server for StackMap — the curated map of the open-source AI stack. Search 344 human-reviewed repos across 21 topics, 817 typed relationships (complements / alternative / built_with), and the written why behind every connection.

A-MEM Agentic Memory System - MCP Server for IDE Integration (Cursor, VSCode) | Dual-Storage: ChromaDB + NetworkX DiGraph with explicit typed edges | Based on Zettelkasten

Local, relation-first knowledge space: typed n-ary relations with immutable history in one SQLite store. Rust desktop, CLI, MCP and REST; offline by default, with optional local LLM support.