#
Starred repositories
626
results
for source starred repositories
Clear filter
MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model
Generate types and converters from JSON, Schema, and GraphQL
PyByntic extends Pydantic with binary-typed fields and automatic byte-level serialization. Define models using familiar Pydantic syntax and turn them into compact binary payloads with full control …
🎒 Token-Oriented Object Notation (TOON) – JSON for LLM prompts at half the tokens. Spec, benchmarks & TypeScript implementation.
TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's …
Grab any element on in your app and give it to Cursor, Claude Code, etc
The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
A universal MCP (Model Context Protocol) server to integrate any API with Claude Desktop using only Docker configurations.
Ultrafast serverless GPU inference, sandboxes, and background jobs
Huma REST/HTTP API Framework for Golang with OpenAPI 3.1
DuckDB-powered Postgres for high performance apps & analytics.
A lightweight LMM-based Document Parsing Model
openblack is an open-source game engine that supports playing Black & White (2001).
Executes commands in response to file modifications
The most intuitive desktop API client. Organize and execute REST, GraphQL, WebSockets, Server Sent Events, and gRPC 🦬
The most mature backend framework for Deno. Create awesome HTTP and WebSocket server as well as KVQueue workers !
A small rust library for adding custom derives to enums
Use Claude Code from any ACP client such as Zed!
Python Implementation of MUVERA (Multi-Vector Retrieval via Fixed Dimensional Encodings)
FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus Agent Tools, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae…
AirLLM 70B inference with single 4GB GPU