Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
Repository Index
142,273 visible repositories in the index
1–4 of 4 · Most stars
Universal AI context generator. Saves thousands of tokens per conversation in Claude Code, Cursor, Copilot, Codex, and more.
Save tokens. Maximize context, Safely
- acceleration
- claude-code
- cursor
- token-reduction
MCP server for Git with local Ollama — zero tokens for git operations
- ai-agents
- claude-code
- conventional-commits
- developer-tools