# cohere-ai/cohere-toolkit

Cohere Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.

Repository: https://github.com/cohere-ai/cohere-toolkit
Canonical: https://ross.abutalabs.com/products/cohere-toolkit
Language: TypeScript
License: MIT
License Family: permissive
Archived: true
Last push: 2026-03-31T13:26:56+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 75, release rhythm 40, longevity 61
- inputs: {"age_days": 866, "days_push": 155, "days_rel": 572, "gap_med": 17, "n_releases_24m": 8}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3177, forks 429 (observed 2026-08-28T04:07:47.676700+00:00)

## What it is
Cohere Toolkit is a deployable all-in-one RAG application with prebuilt frontend and backend components for building LLM-based products. It ships with integrations for tools like Slack, GitHub, Gmail, and Google Drive, plus model provider configuration and theming.

## Use cases
- build a RAG chatbot over company documents
- deploy a self-hosted LLM chat interface
- create an AI assistant with Slack and GitHub integrations
- prototype an LLM product with a ready-made UI
- connect LLM apps to Google Drive or Gmail
- add custom tools with authentication to a chat app

## When to choose
- you want a full-stack, deployable RAG app out of the box
- you're building on Cohere models or want pluggable model providers
- you need prebuilt integrations with common workplace tools
- you want a customizable chat UI plus backend API

## When to avoid
- you only need a lightweight LLM client library
- you want a minimal RAG pipeline without a full UI and database
- you need a framework-agnostic backend in a language other than Python/TypeScript
- you require a fully managed SaaS rather than self-hosting

## Facets
- artifact type: framework
- maturity: active
- function: rag, chatbot, web-framework, agent-framework, llm-inference, self-hosted
- domain: large-language-models, chatbots, web-development, self-hosted
- platform: self-hosted, cross-platform
- tags: cohere, rag-application, llm-ui, deployable-chat, typescript-frontend, python-backend, retrieval-augmented-generation, ai-agents, docker, web-server

## Member repositories
- cohere-ai/cohere-toolkit (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:47.676700+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 2026-08-29T18:45:24.267736+00:00, confidence not recorded.
  - readme: https://github.com/cohere-ai/cohere-toolkit (fetched 2026-08-28T04:07:47.676700+00:00, sha 4b1afa517e83)
- Data as of 2026-08-30T08:39:29.467469+00:00.