Search
Everything in the catalog
Showing 1–24 of 249
- 0.888score
Firecrawl
Firecrawl
API to search, scrape and interact with the web for AI agents, open source and available as a hosted service.
InfrastructureAFreshness: A★ 194.9Kscraping - 0.885score
Ollama
Ollama
Runs open models locally or in the cloud, with a REST API and Python and JavaScript libraries.
InfrastructureAFreshness: A★ 184.6Kinference - 0.883score
vLLM
vLLM project
Fast, easy-to-use open-source library for LLM inference and serving, with an OpenAI-compatible server.
InfrastructureAFreshness: A★ 95.3Kinference - 0.879score
Crawl4AI
Crawl4AI
Open-source web crawler that turns pages into LLM-ready Markdown, with an optional hosted cloud API.
InfrastructureAFreshness: A★ 86.2Kscraping - 0.876score
RAGFlow
InfiniFlow
Open-source RAG engine with document ingestion, hybrid search and visual agent workflows.
InfrastructureAFreshness: A★ 92.8Kdata - 0.875score
Docling
Docling project (LF AI & Data)
Open-source document conversion library that turns PDFs, Office files and audio into structured data.
InfrastructureAFreshness: A★ 69.5Kdata - 0.874score
llama.cpp
ggml.ai
Plain C/C++ LLM inference engine that runs quantized models on many hardware backends, with an OpenAI-compatible server.
InfrastructureAFreshness: A★ 132.2Kinference - 0.872score
MinerU
OpenDataLab (Shanghai AI Lab)
Document parsing engine for LLMs and agents, turning PDFs, Office files and web pages into Markdown or JSON.
InfrastructureAFreshness: A★ 82.4Kdata - 0.871score
Pathway
Pathway
Python framework for live data processing and RAG pipelines that run on a Rust engine.
InfrastructureAFreshness: A★ 62.1Kdata - 0.870score
Mem0
Mem0
Long-term memory layer that lets AI assistants and agents keep user context across sessions.
InfrastructureAFreshness: A★ 67.7Kmemory - 0.870score
Elasticsearch
Elastic
Elasticsearch as a vector database, combining vector search with hybrid lexical search, filters and reranking.
InfrastructureAFreshness: A★ 78.4Kvector db - 0.867score
LiteLLM
BerriAI
Open-source AI gateway with a Python SDK that calls 100+ LLM providers through the OpenAI format.
InfrastructureAFreshness: A★ 62Kgateway - 0.860score
Kong AI Gateway
Kong
Cloud-native API, LLM and MCP gateway with multi-LLM routing, AI analytics and an extensible plugin system.
InfrastructureAFreshness: A★ 44.3Kgateway - 0.856score
LocalAI
LocalAI
Open-source AI runtime that runs text, voice, image and agent workloads on your own hardware behind OpenAI-compatible APIs.
InfrastructureAFreshness: A★ 49.9Kinference - 0.856score
Agent Browser
Vercel Labs
Browser automation CLI for AI agents, built as a native Rust binary.
InfrastructureAFreshness: A★ 44.5Kbrowser - 0.853score
Anyscale
Anyscale
Managed Ray platform for distributed training, batch inference and data processing on GPU clusters.
InfrastructureAFreshness: A★ 44.1Kinference - 0.853score
Hindsight
Vectorize
Agent memory system that helps agents learn over time through retain, recall and reflect operations.
InfrastructureAFreshness: A★ 53.4Kmemory - 0.851score
Marker
Datalab
Open-source tool that converts PDFs, images and Office files to markdown, JSON, chunks and HTML.
InfrastructureAFreshness: A★ 40.6Kdata - 0.851score
Faiss
Meta
Library for efficient similarity search and clustering of dense vectors, with optional GPU support.
InfrastructureAFreshness: A★ 41.2Kvector db - 0.848score
LightRAG
HKU Data Intelligence Lab
Simple and fast retrieval-augmented generation library with several chunking strategies and storage backends.
InfrastructureAFreshness: A★ 40.3Kdata - 0.848score
SGLang
SGLang project (LMSYS)
Open-source inference framework for LLMs and multimodal models, built for agentic workloads and large-scale serving.
InfrastructureAFreshness: A★ 37.7Kinference - 0.843score
Cognee
Topoteretes
Open-source AI memory platform that turns documents, code and conversations into a knowledge graph for agents.
InfrastructureAFreshness: A★ 32.7Kmemory - 0.843score
Qdrant
Qdrant
Open-source vector similarity search engine and database written in Rust, with a managed cloud.
InfrastructureAFreshness: A★ 35.2Kvector db - 0.843score
Lightpanda
Lightpanda
Headless browser built from scratch in Zig for AI agents and automation, not based on Chromium.
InfrastructureAFreshness: A★ 36.9Kbrowser