Build stateful agents that manage their own memory and continue working across long-running interactions.
Memory
Back to discovery
Atom feed
Letta
Nanobot
Commonly
Memory
E C C
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Worth exploring for
Persistent context and long-running agents
In our collection
0 releases
Source
Official GitHub release feed
Follow the changes
The release trail
Original notes, ready to explore. Open a release to see what changed.
No releases collected yet.
This doesn’t mean development has stopped. Check the original repository for the full history.
View releases on GitHubA collected snapshot, not the complete archive.
Keep connecting the dots
There’s more where that came from.
Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps
MemoryOpen-source room for humans + cross-vendor AI agents. Every agent gets its own name, memory, skills, and workstation. Any runtime, your infra — no per-agent fees.
Memory