AgentRecall
mcp-serverNo score yet
Persistent, correction-driven memory for AI agents. Cross-session, cross-platform (Claude Code, Codex, Gemini — any MCP client). Learns from mistakes, compresses context to save tokens, consolidates knowledge overnight. npm: agent-recall-mcp
Stars
303
Δ stars 7d
—
Δ stars 30d
—
Forks
52
Contributors
1
npm DL / wk
—
PyPI DL / wk
—
Language
TypeScript
Last push
2026-06-17
About AgentRecall
Your agent doesn't just remember. It learns how you think. 你的 agent 不只是记得。它在学你怎么想。 Every correction saved is a mistake never repeated. Every insight compounded is tokens never wasted rebuilding context.每一次纠正都是不会重复的错误。每一次复合都是不会重建的上下文。 Persistent, compounding memory + automatic correction capture. MCP server + SDK + CLI. EN: Why · Memory · Install · Tools · Compounding · Phase 6 · SDK · CLI · Arch | 中文: 什么 · 记忆模型 · 安装 · 工具 · 复合 · 新增 Memory is the mechanism. Understanding is…
Read the full README on GitHub →
AgentRecall alternatives
Projects in the same category, closest in size — picked by data, not opinion.
See all mcp-server projects ranked by growth →
Frequently asked questions
- Is AgentRecall still maintained?
- Yes — actively maintained. The last push was on 2026-06-17, with 1 contributors.
- What are the best AgentRecall alternatives?
- Closest by category and size in our data: Zapier MCP, io.github.Lyellr88/marm-mcp-server, cyberchitta/llm-context.py — full list with live signals above.
Topics
Embed this badge
Show your project's live signal in your README — it updates weekly with the data.
Tracked since 2026-06-17 · data as of 2026-06-18 · 27 open issues · 7 releases