Like a human brain: it quietly distills facts as you chat, updates them over time without forgetting history,
and at question time pulls only the relevant slice — answering more accurately on 1/8 the context.像人脑一样:聊天时悄悄提炼「事实」、随时间更新而不忘历史、
提问时只取出相关的一小片 —— 用 1/8 的信息,答得反而更准。
Real numbers · strict DeepSeek judge · every figure you can reproduce yourself真实数据 · 严格的 DeepSeek 判分器 · 每个数字都能自己跑一遍验证
Every new session, the AI forgets who you are. The naive fix is to replay the whole history — but that's slow, expensive, and "lost in the middle" makes it misread.每开一段新对话,AI 就不记得你是谁。最笨的补救是把所有历史重新塞进去 —— 但这又慢又贵,还会"迷失在中间"读串。
Two paths, like the brain: System-1 jots things down as you chat (<50ms, never blocks you); System-2, like sleep, distills memory, builds the graph, and resolves contradictions in the background.和人脑一样分两条路:System-1 边聊边快速记下(<50ms,不卡你);System-2 像睡觉时一样,在后台把记忆提炼、建图、解决矛盾。
Most systems either cross wires or overwrite the old value. Engram marks the old fact "past" and the new one "current" — so it answers "now" correctly and still remembers "then".大多数系统要么记串、要么直接覆盖旧信息。Engram 把旧事实标成"历史"、新事实标成"当前" —— 既答得对"现在",又记得住"过去"。
With provenance: every fact answers "where did this come from?" and "what did it replace?" — auditable, not a black box.还带"溯源":每条事实都能回答"它从哪来""替换了谁" —— 不黑盒、可审计。
Asked "where do I work now?" — the naive way re-reads all 50 sessions; Engram pulls just the relevant facts + a few raw snippets. Less noise, sharper model.问"我现在在哪上班?"时 —— 笨办法把 50 段对话全读一遍;Engram 只取出相关的几条事实 + 几段原文。去掉噪声,模型更聚焦。
LongMemEval_S · 500 questions · graded by a standard, strict DeepSeek judge — a fair number, not a friendly one.LongMemEval_S 基准 · 500 题 · 用标准、严格的 DeepSeek 判分器,所以是公平的数字 —— 不是换个宽松判分器自我安慰。
| System系统 | Overall总分 | Avg tokens平均 token | Open source?开源? |
|---|---|---|---|
| Engram (this project)(本项目) | 83.6% | 9.6k | ✅ AGPL-3.0 |
| Full-context (same backbone)裸塞全文(同 backbone) | 73.2% | 79k | — |
Where it stands: Engram beats full-context by +10.4 at ~8× fewer tokens — fully open, reproducible, cost flat as history grows. 83.6% on the official 500-question judge, every per-question log published.它的定位:Engram 远超裸全文(+10.4 分)且省约 8 倍 token,全开源、可复现、历史再长成本也不涨。500 题官方判分 ≈83.6%,每题原始日志公开。
From write to consolidation to retrieval — layered, reproducible, cost stays flat as history grows; every capability has code and unit tests behind it.从写入、固化到检索,逐层设计、可复现、成本随历史增长保持平稳 —— 每个能力都有对应的代码和单元测试。
Everything pluggable: LLM / embedder / vector store / graph store sit behind interfaces with zero-dep offline fallbacks — pytest passes green with no key and no services.一切可插拔:LLM / 嵌入器 / 向量库 / 图库都在接口背后,带零依赖离线兜底 —— 不用 key、不用任何服务即可 pytest 全绿。
Pick any Bearer key — that's your private memory namespace. Or pip install and self-host, data entirely on your own machine.Bearer key 随便起一个,它就是你的私有记忆空间。也可以 pip install 自部署,数据全在自己机器。
MCP (persistent memory for Claude Desktop / Cursor): pip install "engram-memory[mcp]" && python -m engram.mcp · SDK / OpenAI-compatible: point your base_url at the address above · full API in the repo's API.md.MCP(给 Claude Desktop / Cursor 加持久记忆):pip install "engram-memory[mcp]" && python -m engram.mcp · SDK / OpenAI 兼容:把 base_url 指到上面这个地址即可 · 完整接口见仓库 API.md。