Google PageRank for AI agents. 25,000+ tools indexed.

funes MCP Server

huggingface/funes

Score: 76.8 Rank #2745 MCP Server
[![AgentRank](https://agentrank-ai.com/api/v1/badge/huggingface--funes)](https://agentrank-ai.com/tool/huggingface--funes/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
Are you the maintainer of huggingface/funes? Claim this listing →

Durable, searchable memory of your past agent sessions.

Add AgentRank to Claude Code Discover and compare tools like huggingface/funes — your AI finds the right one automatically
Get API Access →
claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

huggingface/funes is a Rust tool licensed under Apache-2.0. Durable, searchable memory of your past agent sessions. Topics: agent-memory, claude-code, codex, lance, llm-agents, mcp, rust, ai-agents, hermes, pi.

Ranked #2745 out of 24846 indexed tools.

Ecosystem

Rust Apache-2.0
agent-memoryclaude-codecodexlancellm-agentsmcprustai-agentshermespi

Score Breakdown

StarsFreshnessIssue HealthContributorsDependents
Stars 15% 555

555 stars → growing community

Freshness 25% 1mo ago

Last commit 1mo ago → recently updated

Issue Health 25% 46%

11/24 issues closed → many open issues

Contributors 10% 8

8 contributors → small team

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A
PyPI Downloads N/A
Forks 48
Description Good
License Apache-2.0

Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →

How to Improve

Description low impact

Expand your description to 150+ characters for better discoverability

Issue Health high impact

You have 13 open vs 11 closed issues — triaging stale issues improves health

Dependents medium impact

No downstream dependents detected yet — adoption by other projects is the strongest trust signal

Badge all embed codes →

AgentRank score for huggingface/funes
[![AgentRank](https://agentrank-ai.com/api/v1/badge/huggingface--funes)](https://agentrank-ai.com/tool/huggingface--funes/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
<a href="https://agentrank-ai.com/tool/huggingface--funes/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/huggingface--funes" alt="AgentRank"></a>

Embed Widget docs →

Embed a rich score widget on your site or blog.

<script src="https://agentrank-ai.com/embed.js" data-tool="huggingface/funes"></script>

Matched Queries

topic:mcp

From the README

# funes

**Durable memory for your AI coding agents.** `funes` indexes your past sessions across Claude
Code, Codex, pi, and Hermes and lets any agent recall the past decisions, rationale, and findings.
Your memory is a dataset you can publish to the Hugging Face Hub — then any machine, teammate, or
agent can recall from it.

*Put a question to a memory and borrow a coding agent to answer it: funes recalls the relevant sessions, hands them over, and you get one grounded answer that names the sessions it drew from — nothing installed. Here it reads the public `huggingface/funes-memory` dataset named right in the command.*

## Features at a glance

- **Your agent recalls your past work.** The model spontaneously uses `funes` to recall prior decisions, rationale, and findings mid-task.
- **One memory across your agents.** Index Claude Code, Codex, pi, and Hermes into a single memory;
  recall spans all of them, and every hit shows which agent it came from.
- **Your memory is a Hugging Fac
Read full README on GitHub →

Get the weekly AgentRank digest

Top movers, new tools, ecosystem insights — straight to your inbox.