WeVisDoc is an end-to-end document parser for page images. Fine-tuned from Qwen3-VL-2B-Instruct and Qwen3-VL-4B-Instruct, it turns a page into structured Markdown, with LaTeX formulas and HTML tables.
Repository Index
47,133 repositories indexed
73–96 of 101 · Most stars
Xolotl (formerly Strata-DSV4.1): run DeepSeek-V4.1-Flash, all 552B, as a local coding agent on one gaming PC (RTX 4090 + 90 GB RAM) at up to ~27 tok/s, 512K context, October 1017 builds included. Plus GLM-5.3-Flash and Qwen3.8. MoE experts tiered across VRAM, pinned RAM and NVMe; OpenAI + Anthropic API.
Make Codex and Claude Code subscriptions go further: a local model router that gives routine agent work to economical models and keeps your strongest model for the hard parts.
- model-routing
- task-routing
- ai-agents
- ai-gateway
Scikit-learn for Recursive Self-improvement (RSI). A modular framework for recursive harness evolution.
- meta-learning
- reinforcement-learning
- rsi
- ai-agents
Aixio Layer v2 recovers editable layers from flat designs where possible. 150-design benchmark vs Canva Magic Layers, Qwen-Image-Layer and GPT-6 Astra Ultra.
- ai-design
- benchmark
- image-to-layers
- layer-decomposition
A Java library to use the OpenAI Api in the simplest possible way.
- httpclient
- java
- openai
- simple
Romanian and Ukrainian child-safety structured-check toolkit and synthetic research records
Unified LLM API, structured data outputs with LLMs, and agent SDK - in PHP
Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.
One API for every LLM: 170+ providers through one client, with a Rust core and native bindings for every major language.
Go AI SDK, the Go way. One unified API across 21+ providers. Streaming, structured output, MCP support, stdlib only. Go AI SDK for AI applications inspired by Vercel AI SDK.
Feather agent harness, training integrations, and evaluation tools for knowledge work
MobiInfer runs 35B-A3B-class MoE models fully on-device on the Qualcomm Hexagon NPU, streaming experts from flash with lookahead scheduling (LES) and DSpark speculation.
TranslatedExamples of bot persona prompts
Structured outputs, vectorization and tool calling for your Ash application
ModelSphere is an open-source LLM inference infrastructure designed to make production-grade model serving simple, efficient, and continuously optimized.
PocketStrike is a privacy-first mobile AI workstation. It combines zero-cloud native on-device GGUF inference (ARM NEON accelerated) │ with frontier cloud LLMs, multi-step ReAct agent tools, Model Context Protocol (MCP) servers, self-evolving cross-session memory, and FLUX neural image │ generation.
The repository host gives no description.
PDF extraction that audits its own output — and certifies any other extractor's, catching pages they silently dropped. Verify signed manifests offline: free, MIT, no account. 0.903 on opendataloader-bench, #2 of 8 engines. 7-tool MCP server.
The Claude companion for Laravel: the Anthropic API behind a facade, with batches, token counting, files, refusal fallback, named connections, events and test fakes, beside laravel/ai.
A Go toolkit for building AI agents and applications across multiple providers. Unified LLM client, agent framework with handoffs, tool calling, streaming, structured output, MCP integration, and cost tracking.
- ai
- golang
- llm
- structured-output
Instruct LLMs to do what you want in Ruby
- ai
- gem
- ruby
- rubyml
🌊 Floom, "The K8s for AI", orchestrates & executes Generative AI pipelines, Empowering Developers and DevOps to focus on what matters.
PHP client for the Anthropic API: messages, streaming, tool use, thinking, web search, code execution, batches, and more.