OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Memory & RAG

Funes

Funes is a Rust command-line tool that indexes AI coding-agent sessions into durable, searchable memory. It supports Claude Code, Codex, pi and Hermes, and can publish memory as a Hugging Face dataset for recall across machines or by teammates.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Funes — OpenViST project profile in Agent Memory & RAG.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Funes when coding work spans multiple agent sessions or supported agent tools and prior decisions need to be searchable. Use Hub publishing when that memory needs to be available to other machines or collaborators.

Who it is for

  • Developers who want coding agents to recall decisions and findings from earlier sessions.
  • Teams or multi-machine workflows that want to share session memory through a Hugging Face dataset.

Documented uses

  • Index sessions from supported coding agents into a shared memory.
  • Retrieve relevant prior decisions, rationale and findings during a later task.
  • Publish memory as a dataset and query it from another machine, agent or teammate.
Before you choose

Requirements & limits

Funes is an Apache-2.0-licensed public repository. The README lists prebuilt binaries for Linux x86_64, Linux aarch64 and macOS Apple Silicon.

  • Funes provides embedding and reranking models locally but no generative model of its own; answer generation uses the connected agent and its model.
  • A shared memory spans supported agents, and each result identifies its originating agent.
  • Funes-created Hub dataset repositories are private by default, while existing repositories retain their visibility.
  • The documented installer checksum detects download corruption or mismatch but does not authenticate the bucket.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Funes and add a supported coding agent

Install the CLI and onboard Claude Code, Codex, pi or Hermes.

Before you start

  • A platform with a matching documented prebuilt binary: Linux x86_64, Linux aarch64 or macOS Apple Silicon.

Steps

  1. Run the documented installer command: the command below.

    Documented command
    curl -fsSL https://huggingface.co/buckets/huggingface/funes/resolve/install.sh | sh

  2. Add an agent with funes add claude, or substitute codex, pi or hermes.

  3. Use funes status to check whether recall is reading your memory.

Expected outcome

Funes is installed and added to the selected agent; the README says onboarding builds an initial index and installs a hook for Claude Code, Codex and Hermes.

Guide limitations

  • The listed prebuilt binaries cover Linux x86_64, Linux aarch64 and macOS Apple Silicon.
  • The initial-index and hook behavior is specified for Claude Code, Codex and Hermes; the README does not make that same statement for pi.
  • The README notes that the release checksum detects corrupt, truncated or mismatched downloads but does not authenticate the bucket itself.
Documentation 1 ↗
Source-based practical guide

Publish a local memory and recall from a Hub dataset

Share Funes memory through a Hugging Face dataset and query that remote memory.

Before you start

  • Funes installed.
  • A Hugging Face dataset repository you own or control and a token with access to it.

Steps

  1. Publish new local-memory chunks with funes push /funes-memory.

  2. Query a remote memory for one call with funes recall "..." --memory /funes-memory.

Expected outcome

The dataset can be used as a remote memory source; access is governed by the repository visibility and token.

Guide limitations

  • Dataset repositories created by Funes are private by default; existing repositories retain their visibility.
  • The README says publishing is blocked if a chunk still contains a secret after credential redaction.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for AI coding assistance

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
FunesIndex sessions from supported coding agents into a shared memory.CLI, Self-hostedFunes is an Apache-2.0-licensed public repository. The README lists prebuilt binaries for Linux x86_64, Linux aarch64 and macOS Apple Silicon.
Continuum — pouyahasanamrejiStore project lessons so coding agents can retrieve them across conversations.CLI, Self-hosted, ServerThe repository documents local Docker Compose and bare-metal development setups. Bare-metal startup requires Node 22.12.0 or later and pnpm 10.33 or later; the Compose path skips these host prerequisites.
HaftRecord the problem a project is solving and the options considered.CLI, Self-hosted
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
huggingface/funes · Official homepage title · retained in its source language
How we review sourcesSuggest a correction