Public catalog
Browse tools
54 shown. Search ranks against problem language; browsing defaults to stronger public signals.
litellm
model router fail over between providers
Verified 2026-08-10 · 53,182 stars
ollama
run open source models fully offline on a laptop
Verified 2026-08-10 · 43,694 stars
open-webui
self-host ChatGPT-like UI over local models
Verified 2026-08-10 · 27,370 stars
vllm
high throughput local model serving
Verified 2026-08-10 · 26,080 stars
langfuse
observe LLM traces in production
Verified 2026-08-10 · 6,855 stars
Llama Cpp Python
run GGUF models in-process via llama.cpp
Verified 2026-08-10 · 6,823 stars
lightpanda
use lightpanda for scraping
Verified 2026-08-10 · 4,292 stars
text-embeddings-inference
use text-embeddings-inference for rag retrieval
Verified 2026-08-10 · 2,251 stars
headroom
use headroom for scraping
Verified 2026-08-10 · 1,814 stars
OpenLLMetry
OpenTelemetry traces for LLM and agent calls
Verified 2026-08-10 · 1,587 stars
FastEmbed
need fast local embeddings without heavy torch
Verified 2026-08-10 · 1,000 stars
mission-control
use mission-control for deploy infra
Verified 2026-08-10 · 975 stars
Langsmith
trace LangChain and custom LLM runs
Verified 2026-08-10 · 345 stars
Batched
batch embedding requests to cut API cost
Verified 2026-08-10 · 1 stars
Anthropic Python SDK
integrate Claude through the supported Python client
Verified 2026-08-10
AnythingLLM
stand up private document chat without assembling a RAG stack
Verified 2026-08-10
AutoGen
build event-driven agents with tools and explicit team patterns
Verified 2026-08-10
BentoML
package a Python model behind a production HTTP service
Verified 2026-08-10
Chatterbox
generate natural text to speech locally for narration and voice workflows
Verified 2026-08-10
CrewAI
coordinate role-based agents across a bounded workflow
Verified 2026-08-10
Easyocr
OCR images and screenshots with EasyOCR offline
Verified 2026-08-10
Embedchain
prototype document ingestion and question answering with minimal glue
Verified 2026-08-10
FastChat
serve and compare chat models behind an OpenAI-compatible endpoint
Verified 2026-08-10
Fireworks AI
call hosted open models through a Python SDK
Verified 2026-08-10
flag-embedding
use flag-embedding for rag retrieval
Verified 2026-08-10
Google Gen AI Python SDK
integrate Gemini models using Google's current unified SDK
Verified 2026-08-10
GPT4All
run a small local GGUF chat model from Python
Verified 2026-08-10
Groq Python SDK
use low-latency hosted inference through an OpenAI-style client
Verified 2026-08-10
Haystack
compose typed retrieval and generation components into a pipeline
Verified 2026-08-10
Helicone
proxy OpenAI calls for cost and latency observability
Verified 2026-08-10
Kokoro-FastAPI
You need an OpenAI-compatible text-to-speech endpoint running on your own hardware so audio never leaves the machine and there is no per-character bill
Verified 2026-08-10
LangChain.js
compose model, tool, retrieval, and streaming steps in TypeScript
Verified 2026-08-10
LM Studio
run and inspect local models through a desktop interface
Verified 2026-08-10
Local Deep Researcher
You need iterative multi-cycle web research on a topic, with gap analysis and follow-up queries, condensed into one cited markdown summary instead of manually running and pasting searches
Verified 2026-08-10
MLC LLM
compile language models for laptops, phones, GPUs, or browsers
Verified 2026-08-10
Modal
run bursty Python or GPU jobs without managing clusters
Verified 2026-08-10
OpenAI Node SDK
integrate the OpenAI Responses API from TypeScript
Verified 2026-08-10
opencode-openai-codex-auth
You already pay for ChatGPT Plus or Pro and want OpenCode to use that subscription for GPT-5.x and Codex models instead of racking up per-token OpenAI API charges
Verified 2026-08-10
Openrouter
route chat completions across many hosted models
Verified 2026-08-10
OpenSERP
Your agent needs live Google or Bing results as structured JSON but a paid SERP API is too expensive per call
Verified 2026-08-10
Pdfplumber
extract PDF tables and text with pdfplumber
Verified 2026-08-10
Piper
generate speech locally without per-character API charges
Verified 2026-08-10
Portkey
AI gateway for logging caching and fallbacks
Verified 2026-08-10
PrivateGPT
run document question answering without sending files to a hosted service
Verified 2026-08-10
Pymupdf
extract text and tables from PDF with PyMuPDF
Verified 2026-08-10
Replicate Python
run a published image, audio, or language model without hosting it
Verified 2026-08-10
Semantic Kernel
expose typed application functions to a model
Verified 2026-08-10
SGLang
serve language or multimodal models at high throughput
Verified 2026-08-10
Text Generation Inference
serve supported Hugging Face models with continuous batching
Verified 2026-08-10
Together Python
call hosted open models through an OpenAI-style Python client
Verified 2026-08-10
Transformers
load, fine-tune, and evaluate pretrained transformer models
Verified 2026-08-10
Truss
package a custom model with its Python and system dependencies
Verified 2026-08-10
txtai
add semantic search to a Python dataset with a small API
Verified 2026-08-10
Vercel AI SDK
build a streaming AI interface in TypeScript
Verified 2026-08-10