开源AI内存 是 AI Skill Hub 本期精选Agent工作流之一。综合评分 7.5 分,整体质量较高。我们推荐使用将其纳入你的 AI 工具库,帮助提升工作效率。
本地优先的AI内存管理,实现可审计的AI工作流
开源AI内存 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
本地优先的AI内存管理,实现可审计的AI工作流
开源AI内存 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:pip 安装(推荐)
pip install openclaw-mem
# 方式二:虚拟环境安装(推荐生产环境)
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install openclaw-mem
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/phenomenoner/openclaw-mem
cd openclaw-mem
pip install -e .
# 验证安装
python -c "import openclaw_mem; print('安装成功')"
# 命令行使用
openclaw-mem --help
# 基本用法
openclaw-mem input_file -o output_file
# Python 代码中调用
import openclaw_mem
# 示例
result = openclaw_mem.process("input")
print(result)
# openclaw-mem 配置文件示例(config.yml) app: name: "openclaw-mem" debug: false log_level: "INFO" # 运行时指定配置文件 openclaw-mem --config config.yml # 或通过环境变量配置 export OPENCLAW_MEM_API_KEY="your-key" export OPENCLAW_MEM_OUTPUT_DIR="./output"
The AI agent memory layer you can audit. Local-first memory governance for AI agents — every context item cited, every exclusion explained, every mutation reversible.
Most AI agent memory systems compete on recall — remember more, retrieve better. openclaw-mem competes on a different axis: governance. It captures agent activity as durable local records (SQLite + JSONL, no external database), then assembles bounded ContextPack bundles where every included memory carries a citation, every excluded memory carries a written reason, and every memory mutation ships with a rollback receipt.
Built sidecar-first for OpenClaw, usable with Claude, Codex, Gemini, and generic agent harnesses.
Not bigger memory — safer, explainable context.
---
| Capability | What you get |
|---|---|
| **Trust-aware packing** | Quarantined/untrusted records are excluded by policy, with written reasons in the receipt — a defense-in-depth layer against memory poisoning |
| **Citations everywhere** | Every packed item traces back to its source record; citation coverage is measured |
| **Trace receipts** | Include/exclude decisions are structured JSON, not vibes — auditable after the fact |
| **Rollback** | Memory and skill mutations go through plan → checkpoint → apply → receipt → rollback |
| **Hybrid recall** | SQLite FTS + vector search, with scopes and auditable policies |
| **Temporal facts** | "What is currently true about X" — source-linked assertions, timelines, conflict/staleness lint |
| **Graph query plane** | graph query for upstream/downstream/lineage over a SQLite-derived graph |
| **Local-first** | JSONL + SQLite. No cloud service, no external vector DB required, data stays on your machine |
Advanced opt-in labs (graph routing, GBrain sidecar, governed continuity, Dream Lite, Self Curator engine) stay out of the first evaluation path: Core vs Advanced Labs.
| Time | Path | Where |
|---|---|---|
| 5 min | pip CLI + synthetic proof | [Evaluator path](docs/evaluator-path.md) |
| 30 min | Sidecar install, real capture, first governed pack | [Install modes](docs/install-modes.md) |
| Afternoon | OpenClaw plugin / mem-engine promotion, MCP/Channel A/hooks integration for Codex/Claude/Gemini | [MCP integration](docs/mcp-integration.md), [Channel A](docs/channel-a-file-contract.md), [Lifecycle hooks](docs/lifecycle-hooks.md) |
Honest framing: if you want maximum recall benchmarks, the projects below are excellent — and openclaw-mem is not trying to beat them at that game. It governs what enters your context window.
| Recall-focused memory layers<br/>(mem0, supermemory, mempalace, claude-mem, memory-lancedb-pro…) | openclaw-mem | |
|---|---|---|
| Primary question | "Did the agent remember the right thing?" | "Should this memory be trusted — and can you prove why it's in the prompt?" |
| Inclusion logic | Similarity / relevance scores (opaque) | Explicit receipts with include & exclude reasons |
| Untrusted content | Retrieves whenever it matches | Quarantined by trust policy; exclusion documented |
| Mistake recovery | Delete and hope | Checkpointed mutations with rollback receipts |
| Storage default | Vector DB, often cloud | SQLite + JSONL, local-first |
| Best at | Recall quality, token savings | Auditability, safety, explainability |
They are complementary: openclaw-mem already pushes bounded metadata to LanceDB via its writeback loop, and the long-term direction is governance-as-a-layer over whatever recall engine you prefer.
高质量的AI内存管理项目,值得关注
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
经综合评估,开源AI内存 在Agent工作流赛道中表现稳健,质量良好。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | openclaw-mem |
| Topics | ai-agentsai-memorycontext-engineeringllm |
| GitHub | https://github.com/phenomenoner/openclaw-mem |
| License | MIT |
| 语言 | Python |
收录时间:2026-06-12 · 更新时间:2026-06-12 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端