Ross ROSS = Recommend OSS · open-source software intelligence for agents

puppyone-ai/puppyone

Context drive for your AI agents observed · 2026-08-28

github.com/puppyone-ai/puppyone · homepage · TypeScript · Apache-2.0 (permissive) observed · 2026-08-28

Health v2 · maintenance only

78/100

  • Activity 95
  • Release rhythm 74
  • Longevity 45
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 41.5
  • age_days: 635
  • days_rel: 94
  • days_push: 31
  • n_releases_24m: 3

Full methodology

Adoption not part of the score

1299 stars · 74 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Puppyone is a Git-native context drive for AI agents: a persistent, version-controlled file workspace with per-agent scoped permissions, exposed via MCP, CLI, Git, SSH, REST, and a web app. It can be self-hosted with Docker or used as a hosted cloud service, and mirrors SaaS data (Notion, Slack, Postgres, GitHub, etc.) as files agents can read and write.

Use cases

  • give AI agents persistent memory across sessions
  • share context between multiple AI agents like Claude Code and Cursor
  • mount Notion and Slack data as files for agents via MCP
  • add durable version-controlled state to n8n workflows
  • give LangChain or CrewAI agents a shared file workspace
  • self-host a context store for AI coding agents
  • give each agent scoped read/write permissions on shared files

When to choose

  • your agents lose context between sessions and you need durable, versioned shared state
  • you run multiple agents or frameworks (Claude Code, Cursor, n8n, LangChain, CrewAI) that need to see the same files
  • you want per-agent permissions, audit trails, and rollback on agent file edits
  • you want SaaS data (Notion, Slack, Postgres) materialized as files agents can read

When to avoid

  • you only need a vector database for pure RAG similarity search
  • you want a lightweight in-process memory library with no server to run
  • your agents only work within a single repo and never need cross-session or cross-agent context

Facets

service · maturity active

mcp rag agent-framework file-system version-control self-hosted api-framework webhook developer-tools large-language-models self-hosted self-hosted cloud cli context-engineering context-hosting agent-memory git-native per-agent-permissions saas-connectors file-workspace multi-agent-collaboration ai-agents retrieval-augmented-generation web-server docker macos nodejs

10 sources

Member repositories

RepositoryRoleHealth v2
puppyone-ai/puppyonemain78

For agents

markdown · JSON · MCP: product_card(name="puppyone-ai/puppyone")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem