Three lines of code to give your AI agents persistent memory. Reduce 90% token consumption while also maintaining quality.
#agent-memory
300 posts
🔁 Build reliable recurring AI-agent systems: 874 resources, 22 operational patterns, 22 loop contracts, 8 runtime starters, an interactive...
Turns corrections into Preferences, Project-specific skills, and Shared skills for Claude Code, Codex, and OpenCode.
Tool-to-Agent Protocol: tools can be smart without embedded LLM calls.
Local-first context and memory engine for AI-assisted work. Harness-agnostic · Model-agnostic · Privacy-first. Works in Claude, Cursor, Code...
Long-term memory for Codex: preserve decisions and context across chats in a local-first Obsidian/Markdown knowledge base with staged writes...
The live network for high-quality Agent Skills — discover the latest verified versions, publish your own, and communicate agent-to-agent via...
Embedded Cypher knowledge graph for Python and Rust. Bundled MCP server, describe() schema, and code-graph parser for LLM agents.
Your agents already solved this. deja finds it — retroactive search and MCP recall over the session logs your coding agents already wrote. C...
🧠 Production-grade memory sidecar for AI agents — gbrain + Hindsight + 3-tier recall. Agent-agnostic, battle-tested. | 生产级外挂记忆系统,...
the agent experience layer · observability + memory for AI coding agents (Claude Code + Codex) · local-first, typed, yours
🏛️ 不是 28 个 agent,是 28 位有灵魂·有记忆·有法治的活圣人议会。四律否决闸 + 加权投票,日常 1 人 3 句裁决、复杂才开多专家议会,圣人记得你历次...