360 Secure SkillHub
360 安全技能中心

OpenClaw Ollama Memory

通过修改 OpenClaw 配置文件，把记忆检索的嵌入提供方设为本地运行的 Ollama 与 nomic-embed-text 模型，替代云端嵌入 API；包含拉取模型、校验本地服务、重启网关的步骤，并附进阶调优与常见故障排查参考。

djc00p
djc00p
热度 66.26
最近更新 2026-05-11 17:38:03
分类：知识依赖：第三方 API / 读写文件应用场景：笔记整理 / 工作流

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add openclaw-ollama-memory
Metadata
name
openclaw-ollama-memory
description
Set up local semantic memory search in OpenClaw using Ollama + nomic-embed-text. Free, private, offline-capable. Replaces cloud embedding APIs (OpenAI, Gemini) with a locally-running model. Trigger phrases: ollama memory, local embeddings, private memory search, offline memory, free embeddings, nomic-embed-text.
metadata
{"clawdbot":{"emoji":"🧠","requires":{"bins":["ollama","curl"]},"os":["linux","darwin","win32"]}}

OpenClaw Ollama Memory

Local semantic memory search for OpenClaw using Ollama — free, private, no API key required.

Quick Start

1. Install & Run Ollama

Download from https://ollama.ai, then pull the embedding model:

ollama pull nomic-embed-text

Verify Ollama is running:

curl http://127.0.0.1:11434/api/tags

2. Configure OpenClaw

Edit ~/.openclaw/openclaw.json and add under agents.defaults.memorySearch:

{
  "agents": {
    "defaults": {
      "memorySearch": {
        "provider": "ollama",
        "model": "nomic-embed-text:latest",
        "remote": {
          "baseUrl": "http://127.0.0.1:11434"
        }
      }
    }
  }
}

3. Restart OpenClaw

openclaw gateway restart

Key Points

  • Ollama must be explicit — use provider: "ollama", not "openai". OpenClaw doesn't auto-detect Ollama.
  • No API key needed — runs locally, fully offline.
  • nomic-embed-text — 274MB model, fast, accurate, free.
  • baseUrl format — http://127.0.0.1:11434 (no /v1 suffix, no trailing slash).

Next Steps

  • See references/config-reference.md for advanced tuning (hybrid search, MMR, temporal decay, extra paths).
  • See references/troubleshooting.md for common errors and fixes.