GraphCanon updated 1d · GitHub synced 1d · 36 views this month
Decision brief
OpenPipe is an open-source fine-tuning platform for cheaper model hosting and training, currently in a transition phase.
Good fit when
- If you need to integrate with OpenAI's SDK in Python or TypeScript easily
- When aiming to fine-tune GPT-3.5, Mistral, and Llama 2 models while maintaining OpenAI compatibility
Avoid when
- Avoid if requiring real-time support or updates as development is currently paused for integration of proprietary code
- Not ideal for users needing immediate access to the latest features due to its transition phase
Observed Jul 12, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (817d since push)
- As of 1d
- Provenance
- Not a fork · Organization account
- As of 1d
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
npm install OpenPipe npmHow it fits your stack(7)
Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.
Alternative
Integrates
Relationship graph
Optional deeper exploration of typed edges and category neighbours.
Similar tools
Same-category neighbours not already linked as typed edges.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
Turn expensive LLM-based prompts into cheaper, finely tuned models.
Capability facts
- Languages
- typescript
Source: github.language · Aug 20, 2026
Categories
Graph entities
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Aug 20, 2026)
2. Install [NodeJS 20](https://nodejs.org/en/download/current) (earlier versions will very likelySource link
Source: README excerpt (regex_v1, Aug 20, 2026)
- Easy integration with OpenAI's SDK in both Python and TypeScript.Source link
Tags
README
Note: we’ve temporarily stopped development on the open-source version of OpenPipe to integrate some proprietary third-party code. We hope to make the non-proprietary parts of the repository open again under an open core model once we have the bandwidth to do so!
OpenPipe
Open-source fine-tuning and model-hosting platform.
Use powerful but expensive LLMs to fine-tune smaller and cheaper models suited to your exact needs. Query your past requests and evaluate models against one another. Switch between OpenAI and fine-tuned models with one line of code.
Features
- Easy integration with OpenAI's SDK in both Python and TypeScript.
- OpenAI-compatible chat completions endpoint.
- Fine-tune GPT 3.5, Mistral, and Llama 2 models. Host on-platform or download the weights.
- Model output is OpenAI-compatible.
- Switching from GPT 4 to a fine-tuned Mistral model only requires changing the model name.
- Query logs using powerful built-in filters.
- Import datasets in OpenAI-compatible JSONL files.
- Prune large chunks of duplicate text like system prompts.
- Compare output accuracy against base models like gpt-3.5-turbo.
Supported Base Models
- mistralai/Mixtral-8x7B-Instruct-v0.1
- OpenPipe/mistral-ft-optimized-1227
- meta-llama/Llama-3-8B
- meta-llama/Llama-3-70B
- gpt-3.5-turbo-0613
- gpt-3.5-turbo-1106
- gpt-3.5-turbo-0125
Documentation
- See docs
Running Locally
- Install Postgresql.
- Install NodeJS 20 (earlier versions will very likely work but aren't tested).
- Install
pnpm:npm i -g pnpm - Clone this repository:
git clone https://github.com/openpipe/openpipe - Install the dependencies:
cd openpipe && pnpm install - Create a
.envfile (cd app && cp .env.example .env) and enter yourOPENAI_API_KEY. - If you just installed postgres and wish to use the default
DATABASE_URLrun the following commands:
psql postgres
CREATE ROLE postgres WITH LOGIN PASSWORD 'postgres';
ALTER ROLE postgres SUPERUSER;
- Update
DATABASE_URLif necessary to point to your Postgres instance an
For agents
This page has a .md twin and JSON over the API.