Tools Categories Trending New Compare

RAG / Knowledge Base/

ClawMem

ClawMem

Active·★ 177·MIT·Updated 2026-05-20

★ Trending★ RAG / Knowledge Base★ Memory & Context

On-device context engine and memory for AI agents. Claude Code, Hermes and OpenClaw. Hooks + MCP server + hybrid RAG search.

ClawMem is a local context engine providing retrieval-augmented memory for AI agents like Claude Code, OpenClaw, and Hermes. It combines multiple retrieval and scoring techniques (BM25, vector search, intent classification, graph traversal) to surface relevant context. It integrates via hooks, MCP server, or plugins, and shares a single SQLite vault across runtimes.

#ai-agent-memory#ai-agents#bun#claude-code#context-engine#embeddings#hermes-agent#hybrid-search

$ Install

$ npm install -g clawmem

↗ Visit site ★ GitHub

01

Features

01Retrieval-augmented memory with hybrid search (BM25 + vector + reranking)

02Self-evolving memory notes (A-MEM)

03Local, no cloud dependencies

04Multi-framework integration (Claude Code, OpenClaw, Hermes, MCP)

05Intelligent context surfacing and lifecycle management

02

Compatibility

Linux

Full support

Verified via docs

macOS

Full support

Verified via docs

Windows (WSL2)

Full support

Verified via docs

Windows (native)

Not recommended

Verified via docs

03

Quick start

1

$ npm install -g clawmem

04

Use cases

↳Persistent memory for AI coding assistants across sessions

↳Context-aware development with project-specific knowledge

↳Multi-agent shared memory for collaborative AI workflows

05

Alternatives

mindsdb★ 39.2k

Federated Query Engine for AI - The only MCP Server you'll ever need

Brave Search MCP★ 86.5k

Allow your AI Agent to search the real-time internet using Brave Search API. Essential for getting up-to-date information.

context-mode★ 16.0k

Context window optimization for AI coding agents. Sandboxes tool output, 98% reduction. 12 platforms

Auto-claude-code-research-in-sleep★ 11.0k

ARIS ⚔️ (Auto-Research-In-Sleep) — Claude Code skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation via Codex MCP

agents-best-practices★ 1.1k

Provider-neutral Agent Skill for Codex, Claude Code, and agentic harness design.

The agent environment for long-horizon work, continuity, and self-evolution.

awesome-claude★ 250

HeyClaude is a curated registry and distribution surface for Claude and AI-workflow assets: agents, MCP servers, skills, commands, hooks, rules, guides, tools, jobs, Raycast feeds, static data exports, and an npm MCP package.

initrunner★ 38

Define AI agent roles in YAML and run them anywhere: CLI, API server, or autonomous daemon

See all alternatives →

Related searches

ClawMem Alternatives Best RAG / Knowledge Base Tools 2026 Open Source RAG / Knowledge Base ClawMem Tutorial ClawMem Vs Competitors ai-agent-memory ai-agents bun

Comments

Log in to leave a comment

R
River WilsonMay 11, 2026
Good for developers who want unified memory across multiple AI coding tools.
S
Sage WhiteMay 8, 2026
On-device means no cloud dependency for context storage.
R
Reese WilsonApr 26, 2026
Cross-tool memory means switching between Claude Code and OpenClaw preserves context.
R
Reese LewisMar 14, 2026
On-device context engine and memory for Claude Code, Hermes, and OpenClaw.

On this page

01Features 02Compatibility 03Quick start 04Use cases 05Alternatives

Stats

GitHub Stars★ 177

Last commit1w ago

StatusActive

LicenseMIT

CategoryRAG / Knowledge Base

Trend (30d)

+7↑ 0.8%

Links

Documentation↗Discussion↗Issues↗Releases↗

Deploy on DigitalOcean — Get $200 Free Credit

© 2026 AgentIndex.app|Built by a 10-year iOS Developer.

QYS GitHub Buy me a coffee ☕

Browse by Category

Code Assistant Workflow Automation RAG / Knowledge Base Multi-Agent Browser Automation LLM Infra Dev Tooling Observability

Not affiliated with Anthropic, OpenAI or Microsoft.