CodeGraphContext is an open-source developer infrastructure tool that indexes source code into a continuously updated graph, enabling AI assistants and engineering teams to understand real-world co...
CodeGraphContext is an open-source developer infrastructure tool that indexes source code into a continuously updated graph, enabling AI assistants and engineering teams to understand real-world co...
Perseus Vault is a single ~8MB Rust binary that gives AI agents durable, portable memory across sessions with no Docker, no Postgres, and no cloud. It is MCP-native (55 tools), local-first, and ful...
repowise turns a git repository into machine-readable codebase intelligence for AI coding agents. tree-sitter parses 14 languages into a two-tier dependency graph (files and symbols) with a confide...
Economic infrastructure for sustainable AI-assisted development with ~3,000 monthly npm downloads. In-Memoria is an MCP (Model Context Protocol) server that solves the token efficiency crisis throu...
A leading open-source desktop app for Model Context Protocol (MCP), powered by Gemini and built using Electron. It supports plug-and-play configuration, pre-integrated servers, and free-to-use Gemi...
Live context engine and MCP server for AI coding assistants. Resolves @services, @read, @memory, @list, @drift directives into pre-rendered facts before the AI assistant opens its context file — ...
A zero-dependency CLI tool and MCP server written in Go for surgical, precise file editing from the command line. Supports block-aware editing for Go, Python, Terraform/HCL, Nix and more. Used by A...
tirith is a local, open-source, pre-execution security layer written in Rust. It inspects a command, paste, package install, or AI-agent/MCP tool call BEFORE it executes - the exact moment modern s...
Production codebase knowledge graph engine. Parses 9 languages into Neo4j (12 relationship types) with Qdrant vector search and cross-encoder reranking. Two-phase async indexing pipeline. VS Code e...
A self-evolving open source AI daemon written in Go. Learns through repetition, auto-generates code skills to replace expensive LLM calls, and generates unique visual interfaces from scratch for ev...
Agent Infrastructure Security Bench is an open-source benchmark for evaluating whether tool-using AI agents preserve repository, tool, identity, browser, memory, shell, and payment boundaries under...
Neuroscience-inspired memory system for AI agents. Unlike passive vector stores, MemForge treats memory quality as something that should actively improve over time. It runs a 10-phase 'sleep cycle'...
AI agent orchestration layer. Intent classifier (rule-based + LLM fallback). Multi-source retrieval planner with token budget allocation. Parallel executor with circuit breakers. 5-factor context r...
Kindly Web Search is an MIT-licensed MCP server for AI coding agents such as Claude Code, Codex, Cursor, GitHub Copilot, Gemini, Windsurf, and OpenClaw. It combines web search with robust content r...