Latest Open Source Projects

deepclaude

121
@getAsterisk

deepclaude

TLDR: DeepClaude is a high - performance LLM inference API. It combines DeepSeek R1's reasoning and Anthropic Claude's creative and code generation capabilities, offering features like zero latency, security, high configurability, and is open - source. It allows users to use their own API keys and provides a unified interface to leverage the strengths of both models.

ai anthropic anthropic-claude api chain-of-thought claude deepseek deepseek-r1 llm rust Rust
2025-01-26 Github

gitingest

5,200
@cyclotruc

gitingest

TLDR: GitIngest turns any Git repository into a prompt-friendly text ingest for LLMs. It offers features like easy code context, smart formatting, statistics, a CLI tool (Linux only), and a Python package. It can be self-hosted and is built with technologies like Tailwind CSS, FastAPI, Jinja2, tiktoken, and apianalytics.dev. It welcomes contributions and provides instructions for development.

ai code ingestion Python
2024-11-29 Github

chonkie

2,300
@chonkie-ai

chonkie

TLDR: Chonkie is a lightweight and fast RAG chunking library with various chunkers. It offers features like minimal default installs and supports multiple tokenizers. It has better size and speed compared to alternatives.

ai chunking rag retrieval-augmented-generation text-processing Python
2024-11-01 Github

open-computer-use

594
@e2b-dev

open-computer-use

TLDR: A secure cloud Linux computer powered by E2B Desktop Sandbox and controlled by open-source LLMs. Supports various LLMs like Meta Llama and OS-Atlas. Operates via keyboard, mouse and shell commands. Easily add new LLMs adhering to OpenAI API specification.

agent ai anthropic claude computer-use llm Python
2024-10-31 Github

RAG_Techniques

11,500
@NirDiamant

RAG_Techniques

TLDR: This repository is a comprehensive collection of advanced Retrieval-Augmented Generation (RAG) techniques. It includes various methods for enhancing RAG systems such as query enhancement, context enrichment, advanced retrieval methods, iterative and adaptive techniques, evaluation, explainability, and advanced architectures.

ai langchain llama-index llm llms opeani python rag tutorials Jupyter Notebook
2024-07-13 Github

firecrawl

23,000
@mendableai

firecrawl

TLDR: Firecrawl is an API service that crawls URLs and converts them into clean markdown or structured data. It offers advanced scraping, crawling, and data extraction capabilities with features like LLM-ready formats, customizability, and more. It also has SDKs for various languages and integrations with multiple frameworks.

ai ai-scraping crawler data html-to-markdown llm markdown rag scraper scraping web-crawler webscraping TypeScript
2024-04-15 Github

fabric

27,884
@danielmiessler

fabric

TLDR: Fabric is an open - source framework for augmenting humans using AI. It addresses the problem of integrating AI into daily life. It helps users collect and integrate prompts ('Patterns') into various activities. It has multiple installation methods, offers a range of commands for different operations, and provides ways to create custom Patterns. It also includes helper apps and web interfaces for better user experience.

ai augmentation flourishing life work Go
2024-01-03 Github

gpt-researcher

15,900
@assafelovic

gpt-researcher

TLDR: GPT Researcher is an autonomous agent for comprehensive web and local research. It produces detailed research reports with citations, addresses issues of misinformation and token limitations in LLMs, and offers features like smart image scraping, long report generation, and multiple source aggregation. It can be installed via various methods and has a multi-agent assistant and enhanced frontend applications.

agent ai automation llms openai python research search webscraping Python
2023-05-12 Github

swarms

4,200
@kyegomez

swarms

TLDR: The swarms repository provides an enterprise-grade production-ready multi-agent orchestration framework. It offers a variety of agent architectures and tools for tasks such as financial analysis, healthcare diagnosis, and task routing. The framework is highly customizable and includes features like sequential and parallel processing, long-term memory integration, and multi-modal capabilities.

agents ai artificial-intelligence attention-mechanism chatgpt gpt4 gpt4all huggingface langchain langchain-python machine-learning multi-modal-imaging multi-modality multimodal prompt-engineering prompt-toolkit prompting swarms transformer-models tree-of-thoughts Python
2023-05-11 Github