reshuibuduo/TMCRA-Agent-Memory

reshuibuduo★ 5Python最后同步: 2026-08-16

在 GitHub 打开

Scope-isolated, graph-based long-term memory engine for AI agents.

README 摘要

TMCRA — Local Agent Memory OS 简体中文 TMCRA gives long-running agents persistent, source-traceable memory across sessions and applications. A user prompt triggers recall from the owner-global and current-project scopes, followed by a USER source record; after the answer, a separate ASSISTANT source record is stored. This repository includes an owner-local runtime. Clone it, choose an OpenAI-compatible API endpoint or a local generation model, and run the complete memory service on 127.0.0.1 . No TMCRA account or production server is required. Feature guide Capability What the user gets Automatic memory loop Recall and USER-source write before the host runs, followed by a separate ASSISTANT-source write Cross-session and cross-application continuity Tools working on the same project share progress without another project leaking into it Project isolation and owner-global memory Project content remains partitioned; explicitly selected user context can be reused across projects Source / Fast / Slow layers Inspectable source records plus derived memory for fast retrieval and deeper relationships Provenance-aware injection Candidate memories, evidence windows, roles, sources, and retrieval…

在 GitHub 查看完整 README →
Agent/智能体agent-memoryai-agentsclaude-codecodex-plugindeepseek-harnessdsh-pluginlong-term-memorylongmemeval

分类