🛠️Klavis AI
Klavis AI: MCP integration platforms that let AI agents use tools reliably at any scale
⭐ Popular: 6k stars, gaining about 4 a week
View on GitHub ↗repo profile
momentum
durability
bus factor = how many people it takes to cover more than half the commits (6 months). 1 is a solo project; higher means the work is spread across a team. top-author share is the single busiest author's slice of those commits.
since we covered it
why it's a big deal
- Gives AI agents a single way to connect to more than 100 prebuilt tool integrations including Gmail, Slack, and GitHub, so builders skip writing and maintaining each MCP connector themselves.
- Ships built-in OAuth2 handling across integrations, removing a common blocker for teams wiring agents into authenticated third-party services.
- Offers both a hosted platform and self-hosted Docker servers under Apache 2.0, so teams can start on the cloud API or run integrations in their own infrastructure.
under the hood
- Organized into distinct pieces: mcp_servers for the integration implementations, mcp-clients for client libraries, and open-strata, a connector layer positioned to optimize the agent's context window.
- Polyglot codebase led by Python at 40 percent with Go at 24 percent, TypeScript at 22 percent, and JavaScript at 12 percent, plus Python and TypeScript SDKs and a REST API for creating server instances.
- Individual MCP servers are distributed as Docker images via ghcr.io, and a local CLI install is available through pipx install strata-mcp; the project also provides MCP Sandbox environments aimed at LLM training and reinforcement learning.
Radar summary, generated from the project's public sources
star history
- PR#19 5k 2025-10-15
- now 6k + 691 since first covered
curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.
understory
Better known than its recent output, coasting a little on attention.
- output, commits & releases
- clout, star velocity
output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →
covered in
-
Infrastructure for scalable MCP integration & route agent tool access reliably
similar projects
compare these →- 🛰️ ACI
ACI.dev is the open source tool-calling platform that hooks up 600+ tools into any agentic IDE or custom AI agent through direct function calling or a unified MCP server. The birthplace of VibeOps.
5k ACTIVE - 🧑💻 superglue
TypeScript · leaner, 2k stars
superglue (YC W25) builds integrations and tools from natural language. Get production-grade tools for long tail and enterprise systems.
2k ACTIVE - 🔗 Composio
TypeScript · 5.1× the stars
Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
30k ACTIVE
comments
Sign in with GitHub to add your blip on Klavis AI.