Explore projects

Self-Hosted Sentry

🔧🔗https://github.com/getsentry/self-hosted

Sentry, feature-complete and packaged up for low-volume deployments and proofs-of-concept

https://github.com/cirruslabs/orchard

Orchestrator for running Tart Virtual Machines on a cluster of Apple Silicon devices

nanochat

🔧🔗https://github.com/karpathy/nanochat

The best ChatGPT that $100 can buy.

🔧🔗https://github.com/All-Hands-AI/OpenHands

🙌 OpenHands: Code Less, Make More

Browser.js

🔧🔗https://github.com/HeyPuter/browser.js

Highly Configurable Browser Environment for the Web

🔧🔗https://github.com/meta-llama/llama-stack-client-python

Python SDK for Llama Stack

Docker Official Images

🔧🔗https://github.com/docker-library/official-images

The Primary source of truth for the Docker "Official Images" program

https://github.com/LibreTranslate/LibreTranslate Free and Open Source Machine Translation API. Self-hosted, offline capable and easy to setup.

rust sdk

https://github.com/agentclientprotocol/rust-sdk

Rust SDK for ACP clients and agents.

🔧🔗https://github.com/cirruslabs/homebrew-cli

Homebrew formula for Cirrus CLI

docker nginx

https://github.com/nginx/docker-nginx-unprivileged

Unprivileged NGINX Dockerfiles docker nginx debian alpine

🔧🔗https://github.com/getzep/zep

Zep | The Memory Foundation For Your AI Stack

🔧🔗https://github.com/langfuse/langfuse-python 🪢 Langfuse Python SDK - Instrument your LLM app with decorators or low-level SDK and get detailed tracing/observability. Works with any LLM or framework

🔧🔗https://github.com/mvisonneau/gitlab-ci-pipelines-exporter

Prometheus / OpenMetrics exporter for GitLab CI pipelines insights

https://github.com/Picovoice/porcupine On-device wake word detection powered by deep learning

🐚 OpenDevin: Code Less, Make More https://github.com/OpenDevin/OpenDevin https://github.com/All-Hands-AI/OpenHands

🔧🔗https://github.com/meta-llama/llama-stack-client-node

NodeJS library for Llama Stack

🔧🔗https://github.com/vllm-project/vllm-spyre

Community maintained hardware plugin for vLLM on Spyre