Starred repositories
Bulk-delete your Discord messages and reactions from your data package
A native .NET LLM inference engine for GGUF models. TensorSharp provides a console application, a web-based chatbot interface, and Ollama/OpenAI-compatible HTTP APIs for programmatic access. It sup…
Video creation tool: Video editing (with extensive AI-assisted features), screen recording, streaming, and screen sharing. 视频编辑（大量AI辅助功能）、录屏、推流、屏幕共享。
cloc counts blank lines, comment lines, and physical lines of source code in many programming languages.
📚 Two books on harness engineering — the design philosophies behind Claude Code & Codex: constraints, query loops, context governance, multi-agent verification. harness-books.agentway.dev
A self-improving RLM agent for coding workflows and long-running autonomous tasks.
The video editor you own, not rent — edit clips from your coding agent (Claude Code, Codex, Gemini); e.g. burn in stylized subtitles.
Quake 4 alpha released for preservation purposes only.
Official evaluation benchmark reports, execution logs, and black-box verification traces for Balder v7
1
Updated Aug 1, 2026
Semantic code search inside VS Code, powered by semble
Local-first CLI that reads your Spec-Driven Development artifacts and recommends the best value-for-money AI model to implement them. Powered by Ollama — your specs never leave your machine.
This code predicts the exact time and price of a future price point, and can also construct a curve of future prices. It can be used to decipher any process that has a graph—for example, a graph of…
Executable, measurable, and reproducible AI4AI toward recursive self-improvement. Home of OpenMLE and Frontis-MA1.
OpenTalking: An industrial-grade open-source AI digital human framework that supports real-time conversation, private deployment, and pluggable models.
A minimal autonomous code-agent CLI built with Qwen Code
Agent skills that fact-check the internet: claim-by-claim verification with sources and a 0-10 BS score for any YouTube video, article, tweet, or PDF
Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook
Connect a local folder to claude.ai — a browser extension (Chrome/Edge), no desktop app, no API key, works on free plan
Run the full 2.78-trillion-parameter Kimi K3 model beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.