codebase-memory

LeanKG: Stop Burning Tokens. Start Coding Lean.

Persistent memory for AI coding agents: decisions, rules, API contracts, and system topology served over MCP to Claude Code, Cursor, Codex, and Gemini CLI. Powers AI pull request review, issue triage, and a local-first code graph that syncs to the cloud. Self-hosted, 100+ models via LiteLLM.

Self-maintaining and persistent codebase memory for AI coding agents — a deterministic AST index plus agent-written notes that flag themselves stale when the code changes. Works with Claude Code, Cursor, and Codex via MCP + CLI.

Multi-repository workflow isolation for Codex Desktop - one verified project-bound task per repo, codebase-memory indexes, and an optional controller with model-class routing, hash-chained ledger, and evidence-backed experience reuse

the memory layer of your codebase. Knows the WHY, the WHAT, the WHERE-IT-BREAKS.

MCP server giving Claude Code, Cursor & Codex permanent AST code memory. 98.9% token reduction. 100% local.

Local-first Markdown memory and knowledge graph for Pi: preserve decisions, recall across sessions, and explore notes with code.

Persistent codebase memory for AI coding agents. MCP server + CLI + dashboard.

Evidence-backed execution harness for AI coding agents: plans, gates, artifacts, codebase memory, learning loop, and verified claims.

DeepSeek Harness plugin that gives coding agents a real code graph: six MCP tools for symbol search, AST snippets, call-path tracing, architecture analysis, and an auto-started graph UI.

Tu código, convertido en memoria viva para cualquier IA: una araña 3D teje el grafo de conocimiento de tu repo y tu agente lo consulta por MCP.

Local AI agent memory layer for repeated developer tasks, fresh context packets, and low-token repo recall.

Universal multi-agent operating system for Google Antigravity, Gemini CLI, and Claude Code with 503+ pre-staged skills and 71 specialist agents across 23 canonical repositories.

AI-native version control in Rust — continuous capture, encrypted knowledge graph, agent governance

Pi-agent wrapper around codebase-memory-mcp: derived code knowledge (call graphs, blast radius) over a harness-owned trust boundary

Design memory for AI coding.

Markdown wiki with full revision history, REST API and a built-in MCP server. Long-term codebase memory for coding agents — the companion layer to codebase-memory-mcp: the graph knows where code lives, go-wiki knows what it is for. Single Go binary.

Personal research lab: low-level systems experiments on macOS — a FASM x86-64 runtime and tools, a native GPT-2 runtime, and preregistered studies of KV-cache and hidden-state transfer between language models.

Local code intelligence and project memory for Codex and Claude Code. Explore TypeScript, JavaScript and Prisma through call graphs, model usage and source context. Project-scoped MCP server with a shared CLI.

Persistent codebase memory for AI coding agents via inline @agent notes, repo-local skills, and lightweight Codex hooks.