A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
Repository Index
47,133 repositories indexed
73–96 of 277 · Most stars
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
- attention-mechanism
- deep-learning
- gpt
- gpt-2
Sub-50mb agentic, voice and vision intelligence for consumer devices.
- cactus
- llm
- on-device-ai
- edge-ai
Graph-Native Infrastructure for Context and Accountable AI Systems
- ai
- ai-governance
- artificial-intelligence
- context-engineering
A very simple framework for state-of-the-art Natural Language Processing (NLP)
structured outputs for llms
- openai
- python
- pydantic-v2
- openai-functions
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
LangChain4j is an idiomatic, open-source Java library for building LLM-powered applications on the JVM. It offers a unified API over popular LLM providers and vector stores, and makes implementing tool calling (including MCP support), agents and RAG easy. It integrates seamlessly with enterprise Java frameworks like Quarkus and Spring Boot.
💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows
- python
- search
- nlp
- semantic-search
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
- nlp
- embedding
- bert
- ernie
Translated📡 Your own AI-powered news radar. Generates daily briefings in English & Chinese. | Build your own exclusive news radar with AI
- aggregator
- news
- llm
- python
Fastest and only macOS Dictation app with on-device STT and custom trained AI enhancement model. Windows, iOS testflight! Android, Linux waitlist open! A local Wispr Flow alternative. Follow https://x.com/fluidvoiceapp for more
🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP
- bert
- sentence-encoding
- deep-learning
- clip-model
The open-source agent for CI/CD reliability.
- alerting
- datadog
- grafana
- observability
Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.
- llm
- llmops
- model-inference
- fine-tuning
Retrieval and Retrieval-augmented LLMs
- embeddings
- information-retrieval
- llm
- sentence-embeddings
BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive features include: GenAI workflow, RAG, Agent, Unified model management, Evaluation, SFT, Dataset Management, Enterprise-level System Management, Observability and more.
Low-code framework for building custom LLMs, neural networks, and other AI models
TranslatedA-share data for AI agents: K-lines, ticks, reports, fund flow, news, financials, filings, options, macro, futures, events, convertibles | 15 layers·87 endpoints·34 sources. Full-stack A-share data toolkit: market quotes and K-lines · same-day tick-by-tick trades · research reports · signals · capital flow · news · financials · announcements · limit-up board trading (打板) · ETF options · public sentiment · macro and interest rates · futures and block trades (including Dalian Commodity Exchange daily K-lines) · event-driven · convertible bonds | No API key needed except for iwencai
- a-share
- ai-agent
- ai-skill
- china-stocks
Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.
PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
- mupdf
- xps
- pdf-documents
- epub
OpenAI, GPT 6.1, GPT-Image-2, Whisper API clients for Go. Zero-dependency.
- go
- openai
- golang
- streaming-api
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.
- avx2
- c99
- cpu-inference
- deep-learning