Skip to main content
PuppyOne hero visualization
new
PuppyOne logo

puppyone - versioned file workspace for ai agents

About PuppyOne

A file system for agents rather than a vector store: it pulls Notion, Slack, Gmail and Postgres into one versioned tree of readable files, hands each agent a scoped access point, and keeps Git-style history over what they change. Reachable through MCP, a CLI and an API, so Claude Code and Cursor read and write the same tree. The Community Edition is Apache 2.0 and self-hostable with no seat fees, which is the version worth trying first if the point is keeping context on your own machine.

Key Capabilities

Agent context as versioned files you can read, not embeddings you cannot

Git-style history over what each agent changed, so a bad run is reversible

Scoped access points per agent instead of handing every agent the whole tree

Ingests Notion, Slack, Gmail and Postgres into that same tree

Community Edition is Apache 2.0 and self-hostable with no seat fees

Perfect for

Multi-agent setups
Self-hosters
MCP users

Compare PuppyOne

Community Buzz

Community Buzz

No recent posts yet

We are monitoring X for fresh discussions about PuppyOne.

Similar Tools to PuppyOne

Vibe Kanban logo

Vibe Kanban

Open-source kanban board for orchestrating AI coding agents. Plan tasks as issues, run Claude Code, Codex, or Gemini CLI in isolated git worktrees, review diffs inline, and open pull requests from one local UI. The company behind it (bloop) shut down in April 2026, but the project lives on as community-maintained open source and local workspaces keep working.

freemium · $30+
Hermes Agent logo

Hermes Agent

Self-hosted autonomous agent from Nous Research with a built-in learning loop. Creates skills from experience, persists memory across sessions, and runs 24/7 on your own hardware with sandboxed terminals and messaging-app gateways.

free
Moadim logo

Moadim

A loop engine that runs coding agents on a schedule against your codebase. A loop pairs a prompt, a schedule and an agent (Claude, Codex, Hermes, NanoClaw or Pi), and each run executes in a throwaway workbench so a hung run gets killed rather than left behind. Everything is exposed twice, as a REST endpoint and as an MCP tool, so another agent can schedule work as easily as you can. Routines live in ~/.config/moadim/ and are git-trackable. It runs entirely on your own machine: no cloud, no account, no data leaving the host.

free
OKF Agent Memory logo

OKF Agent Memory

Persistent memory for coding agents kept as plain files in your repository rather than in a vector database. It implements Google's OKF v0.2 specification with progressive disclosure, so the agent pulls in only the slice of memory a task needs instead of paying for the whole store on every request, and retrieval uses BM25 rather than embeddings. Because the memory is git-native it diffs, reviews and reverts like the rest of your code, and it publishes its own security documentation, which is unusual for a tool whose entire job is persisting context to disk.

free
Slotstream logo

Slotstream

Runs mixture-of-experts models that do not fit in a Mac's memory by streaming the experts it needs from SSD, so a 105 GB model can run on a 48 GB machine. Apple Silicon only, built on MLX, and focused on one model family rather than being a general local-model runner. Treat the throughput and SSD-wear figures as the project's own measurements: they are published and detailed, and no independent verification exists yet. The project is weeks old and moving quickly. Sevra, listed as its homepage, is a future consumer app built on top of it rather than a paid tier of it.

free
9Router logo

9Router

Self-hosted router that puts one OpenAI-compatible endpoint in front of many model providers, so Claude Code, Codex, Cursor, Cline and Copilot keep working when a subscription hits its quota. Runs as a local Next.js service on localhost:20128 with its own dashboard, compresses tool output before it reaches the model, and falls back across three tiers of provider. Read the security section before you point a real key at it: nineteen security advisories have been published on the repository, all in July 2026, several of them authentication bypasses in the proxy itself.

free
Rather have someone build it with PuppyOne for you?

Browse vetted vibe coding agencies for MVP builds, cleanups, and audits.

// start building today

ready to try puppyone?

go to the official site and judge PuppyOne yourself.

try puppyone now
Free forever for evaluation: one member, one project, three agent access points, 2 GB and 30-day history. Developer $19 per workspace per month adds three projects, ten access points, 25 GB, 180-day history and CLI, API and MCP access. Team $99 covers ten members, twenty projects, a hundred access points and 250 GB. Enterprise is custom and adds SSO, self-hosted or VPC deployment and an SLA. The Community Edition is Apache 2.0 with no usage limits and no seat fees. Read from the vendor's pricing page on 2026-09-14.
Explore options

PuppyOne Alternatives

See how PuppyOne compares to similar tools.