# yomorun/yomo

🦖 Serverless AI Agent Framework with Geo-distributed Edge AI Infra.

Repository: https://github.com/yomorun/yomo
Canonical: https://ross.abutalabs.com/products/yomo
Homepage: https://yomo.run
Language: Rust
License Family: other
Topics: realtime, quic, serverless, distributed-cloud, geodistributedsystems, yomo, function-calling, openai, a2a-protocol, claude-code, mcp, agent-framework, skills, managed-skills
Last push: 2026-08-25T02:34:26+00:00

## Health v2 (maintenance only)
Score: 98/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 97, longevity 100
- inputs: {"age_days": 2254, "days_push": 9, "days_rel": 21, "gap_med": 12.0, "n_releases_24m": 43}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1920, forks 148 (observed 2026-08-28T04:05:55.161219+00:00)

## What it is
YoMo is an open-source serverless LLM function calling framework for building fast, geo-distributed AI agents, written in Rust with a QUIC-based runtime. It lets developers deploy LLM tools/skills (in TypeScript or Go), expose them as MCP servers, and route AI model traffic through an OpenAI-compatible API.

## Use cases
- build ai agents with llm function calling
- deploy serverless llm tools close to users
- expose llm function calling as an mcp server
- run an openai-compatible chat completions endpoint backed by custom tools
- route llm tool calls across geo-distributed edge infrastructure
- use ollama or openai as provider for agent backends

## When to choose
- you need low-latency, geo-distributed execution of LLM tools
- you want to build agents with function calling in TypeScript or Go
- you want MCP server support and OpenAI-compatible APIs in one runtime

## When to avoid
- you need a simple single-process agent without distributed deployment
- you require a permissively licensed dependency (no license file is published)
- your stack is Python-only and you don't want TypeScript/Go tool implementations

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, mcp, rpc, http-server, cli, sdk
- domain: artificial-intelligence, large-language-models, developer-tools, backend, microservices
- platform: windows, cross-platform, cli, self-hosted
- tags: llm-function-calling, serverless, quic, edge-ai, geo-distributed, tool-routing, openai-compatible, a2a-protocol, ai-agents, linux, macos, docker

## Member repositories
- yomorun/yomo (main) score 98

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:55.161219+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:09:50.150285+00:00, confidence not recorded.
  - readme: https://github.com/yomorun/yomo (fetched 2026-08-28T04:05:55.161219+00:00, sha 0e88f3a52583)
  - homepage: https://yomo.run (fetched 2026-08-29T10:49:13.800344+00:00, sha 5525885cf04a)
  - site_page: https://yomo.run/quickstart (fetched 2026-08-29T10:49:13.802017+00:00, sha 5a9cbc0a1728)
  - registry_crates: https://crates.io/api/v1/crates/yomo (fetched 2026-08-29T10:49:13.803598+00:00, sha d41921fb78f4)
- Data as of 2026-08-30T08:39:29.467469+00:00.