convez.ai
MCP ServerAutomaçãoIntermediário
Fergana-Labs

Stash — Memória Compartilhada para Agentes

Fergana-Labs/stash

Base de conhecimento compartilhada para agentes de IA em equipes

Ver no GitHub
BomPluginScore · de 0 a 100

MCP server que cria uma base de conhecimento centralizada para agentes de IA, conectando GitHub, Drive, Gmail, Notion, Slack e outros. Permite que equipes compartilhem contexto de sessões, arquivos e páginas, eliminando duplicação de trabalho entre agentes e acelerando a velocidade de desenvolvimento em até 49%.

Instalação

$npx convez-ai Fergana-Labs/stash

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
344
Forks
46
Acompanhando
3
Saúde
87%
Último commit
há 6 dias
Versão
pr-815-images
Issues abertas
27
Contribuidores
6

Casos de uso

  • Evitar duplicação de trabalho entre agentes rodando no mesmo repositório
  • Manter histórico centralizado de sessões, tentativas e decisões técnicas
  • Consultar contexto de colaboradores sem depender de Git ou comunicação síncrona

Veredito

Stash resolve um problema real em equipes com agentes: fragmentação de conhecimento entre sessões isoladas. Implementação sólida com suporte a múltiplas fontes de dados e prova de conceito comprovada (49% de melhoria em velocity). Exige configuração e integração, mas o ganho em contexto compartilhado justifica para times que rodam agentes em paralelo.

README

A tradução para o português deste README ainda está na fila.

How it works

  • Sessions stream in automatically. A hook for your coding agent pushes every transcript — prompts, tool calls, artifacts — to a shared workspace.
  • Files and sessions live side by side. Markdown, HTML, tables, PDFs. Humans and agents both write here; both sides see edits in real time.
  • Agents query it like a filesystem. A CLI, MCP server, and virtual-filesystem shell expose the workspace to any agent. Semantic and keyword search across pages, sessions, and tables.
  • Skills are the shareable slice. Bundle pages and sessions into one link. Publish to the world, share with collaborators, or fork a public Skill into your own workspace.

Why shared beats individual

When five engineers run Claude on the same repo, they generate valuable session transcripts. However, their coding agent can only access transcripts generated on the machine where the agent is currently running. As a result, engineering effort is duplicated and eng velocity is decreased. This is especially true as coding agents begin to run autonomously for significant periods of time.

With Stash, every agent on the repo has context about every session created from that repo. Here are some use cases:

  • Code Faster / Don't Duplicate Work: "Has anyone else tried fixing the memory leak in our API gateway? What was attempted?"
  • Look Organized During Standup: "What did I get done this week? What other work did I do that isn't tracked in Git?"
  • Don't Be Blocked on Collaborators: "Why did Sam increase the timeout to 30s? The git history is unhelpful."
  • Align With Your Team Faster: "Please add a feedback endpoint to our API" -> Claude: "FYI, Sam decided not to add a feedback endpoint since we want to encourage churned users to hop on a call directly"

"raw data from a given number of sources is collected, then compiled by an LLM into a .md knowledge base, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance it… I think there is room here for an incredible new product instead of a hacky collection of scripts."

— Andrej Karpathy, LLM Knowledge Bases

Stash is that product. The one place your agents connect to all your data, with an agent-native Drive they write it back into — not a stack of shell scripts wrapped around a folder of markdown.

Built for —

Use caseWhat teams put in it
Engineering live docscoding-agent plans, ADRs, and design notes that stay current
Company brainthe shared context every agent and teammate reads from
Research knowledge baselong-running PKBs with sources, transcripts, and tables
Ops playbooksrelease runbooks and on-call procedures
Brand voiceeditorial guidelines and copy standards agents write to
Personal knowledge managementnotes, drafts, and scratch files for a single operator

Quick Start

pip install stashai / uv tool install stashai
stash login

stash login walks you through account creation, picks a workspace, connects your current repo when you want uploads, and wires up coding-agent plugins. Use stash connect later when you are already authenticated and only need to bind another repo to a workspace.

bash -c "$(curl -fsSL https://joinstash.ai/install)"

The installer uses uv to install or update stashai, bootstrapping uv when needed, and then runs stash login. Use this when you don't already have a Python toolchain on your machine.

Then try it: ask your coding agent if it has access to Stash.

Agents can browse Stash with an app-level virtual filesystem shell:

stash vfs ls /
stash vfs "tree /workspaces -L 2"
stash vfs "find /workspaces -maxdepth 3 -type f | head -n 20"
stash vfs "rg \"database migration\" /workspaces"

Integrations

Stash supports the following coding agents:

  • Claude Code
  • Cursor
  • Codex
  • OpenCode
  • Gemini CLI
  • Openclaw

Stash supports opt in per-coding agent. stash login can auto-install hooks for Claude Code, Cursor, Codex, and OpenCode; Gemini CLI and Openclaw are available in plugins/ and are installed manually. Mix and match — different teammates can use different agents against the same shared brain.

CLI Reference

See here for a CLI reference.

Self-Hosted

Run Stash with prebuilt GHCR images:

To host locally:

git clone https://github.com/Fergana-Labs/stash.git
cd stash
cp .env.example .env
docker compose -f docker-compose.prod.yml -f docker-compose.local.yml pull
docker compose -f docker-compose.prod.yml -f docker-compose.local.yml up -d
curl http://localhost:3456/health
open http://localhost:3457/login

Docker Compose generates and persists the OAuth token encryption key when INTEGRATIONS_ENCRYPTION_KEY is unset. Set it yourself only if you manage deployment secrets outside Compose.

For a public domain with Caddy and HTTPS:

# Set PUBLIC_URL and CORS_ORIGINS in .env, then replace app.example.com in Caddyfile.
docker compose -f docker-compose.prod.yml pull
docker compose -f docker-compose.prod.yml up -d
curl https://app.example.com/health

docker-compose.prod.yml pins the image versions it was tested with. To upgrade, pull the latest compose file and restart:

git pull
docker compose -f docker-compose.prod.yml -f docker-compose.local.yml pull
docker compose -f docker-compose.prod.yml -f docker-compose.local.yml up -d

Then install the CLI:

pip install stashai   # or: uv tool install stashai
cd /path/to/the/repo/you/want/to/connect
stash config base_url http://localhost:3456
stash login

Use your public URL instead of http://localhost:3456 when connecting to a domain-backed install:

stash config base_url https://app.example.com

Finally see it in action:

claude
> what did I get done last week? check stash.

Privacy

Stash is built for engineering teams working in private repos.

  • LLM calls are optional and scoped. When an Anthropic API key is configured, the server uses it for ask-the-workspace answers and auto-generated session titles. No key means those features are unavailable — the rest of Stash works without any LLM.
  • Permissioned workspaces. Only invited members can access a workspace. Public visibility is controlled by Skills.
  • Transcripts are opt-in. If you don't want to share your agent transcripts, you can give your agent shared read access to the workspace's memory without uploading any of your own session data.

FAQ

What LLMs does Stash use? When an Anthropic API key is provided, the server calls Claude for ask-the-workspace (quality tier) and session title generation. Both are optional — without the key, Stash works but those features are disabled. There is no background page-writing agent.

Can I use this without Claude Code? Yes. You can use the CLI with anything, and Stash has native plugins for Cursor, Codex, Opencode, Gemini CLI, and more.

Contributing

Contributions are welcome. See CONTRIBUTING.md to get started.

Found a bug? Open an issue.

License

MIT — Copyright (c) 2026 Fergana Labs


Ver o original no GitHub

Bom para

Relacionados