# MeetKai/functionary

Chat language model that can use tools and interpret the results

Repository: https://github.com/MeetKai/functionary
Canonical: https://ross.abutalabs.com/products/functionary
Language: Python
License: MIT
License Family: permissive
Topics: ai, function-calling, llm, ml, python, agents, ai-agents
Last push: 2026-06-30T16:05:40+00:00

## Health v2 (maintenance only)
Score: 69/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 90, release rhythm 35, longevity 82
- inputs: {"age_days": 1149, "days_push": 64, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1595, forks 118 (observed 2026-08-28T04:05:09.066866+00:00)

## What it is
Functionary is a chat language model and serving code that interprets and executes functions/plugins, deciding when to call tools in parallel or serially based on JSON Schema definitions. This repository is deprecated and kept only as a reference snapshot of an older version of the project.

## Use cases
- run an llm that calls functions from json schema definitions
- build an ai agent that uses tools and interprets results
- self-host a function-calling chat model
- serve an openai-compatible tool-calling model
- evaluate function calling models on a local gpu

## When to choose
- you need a reference implementation of function-calling model serving
- you want to study how tool-calling prompt templates work

## When to avoid
- you want an actively maintained project - this repo is deprecated
- you need the latest functionary models or support
- you expect bug fixes or reviewed pull requests

## Facets
- artifact type: library
- maturity: abandoned
- function: llm-inference, agent-framework, chatbot, prompt-engineering
- domain: large-language-models, artificial-intelligence
- platform: python, self-hosted
- tags: function-calling, tool-use, openai-compatible, deprecated, language-model, ai-agents, gpu

## Member repositories
- MeetKai/functionary (main) score 69

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:09.066866+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 2026-08-30T03:54:05.524868+00:00, confidence not recorded.
  - readme: https://github.com/MeetKai/functionary (fetched 2026-08-28T04:05:09.066866+00:00, sha 42111ae74290)
- Data as of 2026-08-30T08:39:29.467469+00:00.