Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.
Repository Index
47,133 repositories indexed
1–12 of 12 · Most stars
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.
Composable, view-based context for DeepSeek Harness. Pluggable sources and strategies, with layered memory and self-evolving skills out of the box.
- agent-memory
- deepseek-harness
- local-first
- persistent-memory
Remory: Learning Residual Memory for Context Compaction
- context-compaction
- inference
- llm-agents
- residual-memory
The ai agent workflow tool that scales from small, simple projects to large, complex codebases.
- agent
- agent-memory
- agent-orchestration
- agentic-workflow
TranslatedGive your AI a body, and a bit of human touch — a QQ companion chatbot that remembers things and reads the occasion, plus an MCP server that can control Android phones
Neuro-symbolic agents with verified memory. MCP math tools, an algebra repair Skill, and an open challenge. Verify solutions, learn checked rules, and reuse.
- ai-agents
- mathematics
- neuro-symbolic
- reasoning
Long-term, cross-project memory for AI coding agents. Your own Obsidian vault as the source of truth. Daemonless and without opaque databases, your memory belongs to you.
EGC gives every AI coding agent the same brain. Shared memory, skills, and live context across Cursor, Claude Code, Copilot, Aider, and 29 AI coding tools with zero configuration. Every tab, terminal, and AI stays automatically synchronized. One brain. Everywhere.
- ai-agents
- persistent-memory
- mcp
- claude-code
High-fidelity transcript memory for Claude Code — index every session, recall byte-identical, search, prune, compose. Local-first, stdlib-only, MCP.
- claude-code
- llm
- mcp
- memory
Decentralized agent memory for the Lightning economy. Nostr identity, L402 payments, MCP server.
Per-repo memory, outcome telemetry, and a calibrated-confidence gate for Claude Code, with MCP and AGENTS.md projections so other AI coding tools can read its context. Notes survive sessions; success claims need test evidence; your reverts are remembered. Local-only, stdlib runtime.