LeanKG: Stop Burning Tokens. Start Coding Lean.
-
Updated
Nov 8, 2026 - Go
GeezerVisonThe World Wide Web, restored to 800 pixels of glory. |
| Home|About|Gaming cabinet|Archives|How it works|Starter sites |
GeezerVison is showing github.com — Build software better, together
#
codebase-memoryHere are 31 public repositories matching this topic...Language: All
Filter by language
Sort: Most stars
Sort options
LeanKG: Stop Burning Tokens. Start Coding Lean.
mcp knowledge-graph graph-database token second-brain graph-engineer knowlege-base ai-memory mcp-server context-engineer codebase-memory saving-token lean-code lean-context concise-context lean-token memory-ai-agent codebase-memory-mcp
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.
python mcp self-hosted knowledge-graph developer-tools code-review codegraph ai-agents sourcegraph code-intelligence llm coderabbit claude-code cross-repository-intelligence codebase-memory coderabbit-alternative
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.
code-navigation cli tree-sitter typescript memory mcp static-analysis ast code-search persistent-memory cursor knowledge-base codex ai-agents code-intelligence ai-coding model-context-protocol claude-code ai-memory-system codebase-memory
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
windows multi-repo codex workflow-orchestration codex-desktop codex-skill codebase-memory codebase-memory-mcp
the memory layer of your codebase. Knows the WHY, the WHAT, the WHERE-IT-BREAKS.
typescript sqlite mcp time-machine developer-tools rag local-first retrieval-augmented-generation knowledge-preservation ai-memory model-context-protocol mcp-server ai-coding-assistant ghost-code codebase-memory premortem git-archaeology
MCP server giving Claude Code, Cursor & Codex permanent AST code memory. 98.9% token reduction. 100% local.
python tree-sitter mcp ast knowledge-graph developer-tools semantic-search codex page-rank llm-tools token-reduction cursor-ai model-context-protocol claude-code ai-coding-assistant codebase-memory
Local-first Markdown memory and knowledge graph for Pi: preserve decisions, recall across sessions, and explore notes with code.
markdown notepad pi knowledge-graph developer-tools persistent-memory note-taking obsidian local-first agent-memory okf pi-coding-agent codebase-memory pi-weave
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.
developer-tools software-engineering governance autonomous-agents ai-safety evidence ai-agent llm-tools ai-coding coding-agent agent-harness codebase-memory
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.
visualization tree-sitter threejs mcp static-analysis code-analysis knowledge-graph ai-agents claude-code codebase-memory
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.
mcp superpowers developer-tools gemini-cli agentic-ai antigravity mcp-server claude-code google-antigravity codebase-memory
AI-native version control in Rust — continuous capture, encrypted knowledge graph, agent governance
git rust version-control mcp knowledge-graph developer-tools ai-agents ai-memory mcp-server agent-memory codebase-memory
Pi-agent wrapper around codebase-memory-mcp: derived code knowledge (call graphs, blast radius) over a harness-owned trust boundary
cli mcp static-analysis knowledge-graph code-search call-graph ai-agents claude code-intelligence llm agentic-ai model-context-protocol agent-memory claude-code context-engineering codebase-memory
Design memory for AI coding.
developer-tools cli-tool decision-graph llm-tools ai-coding claude-code context-engineering codebase-memory
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.
markdown golang wiki sqlite mcp developer-tools knowledge-base ai-agents mcp-server claude-code code-memory codebase-memory
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.
macos cli homebrew research assembly x86-64 assembler mach-o developer-tools rosetta fasm low-level-programming systems-programming ai-agents kv-cache flatassembler llm binary-tools codebase-memory ragbox
Persistent codebase memory for AI coding agents via inline @agent notes, repo-local skills, and lightweight Codex hooks.
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.
javascript typescript mcp static-analysis postgresql developer-tools call-graph codex bun prisma code-intelligence mcp-server claude-code codebase-memory
CodeMind is an AI agent memory system that maintains persistent, real-time context over complex codebases. By utilizing symbol graph storage, AST chunking, and intelligent file scanning, CodeMind enables LLMs to reason about relationships across large code structures without losing track of dependencies
Add this topic to your repoTo associate your repository with the codebase-memory topic, visit your repo's landing page and select "manage topics." |
| You are visitor 01402503 — GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required. |