Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Repository Index
70,234 visible repositories in the index
1–21 of 21 · Most stars
Context Graph for AI Native SDLC
Persistent memory for Claude Code, Codex and 6 other AI agents, stored as plain markdown in your Obsidian vault. New: Crew, one shared logbook so Claude Code, Codex, Cursor and Grok Bot know what each other did. 48 commands: semantic search, self-rewriting notes, key-less research, scheduled agents.
Lossless Claw — LCM (Lossless Context Management) plugin for OpenClaw
Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc.
AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN
Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.
- agents
- claude-code
- claude-code-cli
- claude-code-hooks
Framework for AI agents to build and maintain a digital brain through Obsidian wiki | Memory System for Agents
- agent-skills
- knowledge-base
- llm-tools
- obsidian
A agent framework based on the tutorial hello-agents
The repository host gives no description.
Official Code of Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
The Open Source Memory Layer For Autonomous Agents
Hivemind turns your traces into reusable skills across agents
Official repository for MemT-1.0
Official code for "Zero-Mem: Zero-Token Memory Operations for LLM Agents".
TranslatedUse the colorful human world to train DSH's personality: by default, letter-style reflections are accumulated in a dedicated human-world.md; connecting with external plugins through DSH is allowed. History, favorites, likes, and coins are each disabled by default; this project does not provide a comment interface.
- bilibili
- dsh-plugin
- humanism
- local-first
Bitemporal AI memory system: six-variable decay, time-graded recall, TTL expiry, dedupe, competitive retrieval (Neo4j + PostgreSQL + Redis)
- agent-memory
- ai
- bitemporal
- graphiti
TranslatedA local memory layer for DeepSeek Harness: those who are raising a "big fat fish" can download it to play with. After testing, once downloaded it feels more human and more natural than using RAG or an external memory store alone.
- dsh-plugin
- dsh-plugin-market
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.
Agentic memory for CTI in Python — STIX knowledge graphs, threat-actor alias resolution, offline-first RAG, MCP server for Claude Code and LangChain agents
- claude-code
- cti
- llm
- rag
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.