Ars Umbris
arsumbris/arsumbrisA malleable, agent-native IDE for typed knowledge.
197in 13 days
+9in 24h
ADEs! Skills! Loops! Graphs! Software Factories!
We're all struggling to keep up. This is a very early attempt to help.
New repos, ranked by how fast they're gaining stars.
A malleable, agent-native IDE for typed knowledge.
197in 13 days
+9in 24h
Pandoc for AI chats. Move ai chats across harnesses: Claude Code, Codex, OpenCode, Cursor, and more. Rust library, CLI, and WASM.
Orchestrate cargo across Claude, Codex, and Cursor so concurrent agent sessions share work instead of fighting locks.
An open-source background agents coding system
Cactus Compute
A 121M-parameter open model for tool calling, structured extraction and text embedding on tiny devices. One set of weights ships as an intelligence ladder: every depth from 2 to 20 layers is a deployable model, an 8-29 MB CQ2-bit binary.
DeepSeek
We introduce DeepSeek-V4.1-Flash, a multimodal Mixture-of-Experts (MoE) model with 552B backbone parameters and support for contexts of up to one million tokens. The model natively processes images and text, and generates text autoregressively.
OpenAI
Our most capable model, built for the hardest end-to-end work.
The software factory approach (a closed agentic loop that runs in the cloud) is growing in popularity, but it can be daunting to adopt.
A new pattern is showing up in context infrastructure: store as much of the underlying history as possible, then build the useful representations of it later.
A useful personal agent should remember your conversations, build lasting knowledge, and learn how you get work done. Take an agent running in Slack as an example.
An occasional email when notable AI dev tools and models land in the directory. No spam, unsubscribe anytime.
Local UI to run and train LLMs and diffusion models, including Kimi K3, MiniMax-H3, Gemma 4, Qwen3.6, DeepSeek-V4, FLUX and more.
Multi-agent workflows with full observability and time travel. Watch every step live; rewind, fork, or replay any run. Any model, any harness.
The pretty much "official" DSPy framework for Typescript
Hermes Agent — a standalone terminal app and a native application for macOS, Windows, and Linux. Install it and start a conversation with the agent that grows with you.
Multiplayer agent harness for work
A self-improving RLM agent for coding workflows and long-running autonomous tasks.
An open-source database of AI models.
Native Agent CLIs manager for macOS. Ghostty Terminals + Codex App Features/UX = Ghostex! Embedded browser & IDE. Strong agents support.
Fast Rust library for PDF inspection, classification, and text extraction. Intelligently detects scanned vs text-based PDFs to enable smart routing decisions.
The AI Toolkit for TypeScript, from the creators of Next.js.
A lightweight, cross-platform code editor, built with Tauri (Rust and React) with Git support, AI agents, vim keybindings.
Autonomous coding agent as an SDK, IDE extension, or CLI assistant.
An open-source background agents coding system
Track usage windows, credits, and resets across 56 AI coding providers from your macOS menu bar.
T3 Code is a minimal web GUI for coding agents (currently Codex, Claude, Cursor, and OpenCode, more coming soon).
An open-source Grok Bot. Bring your own agent, local-first, on the models you already have.
A GUI for your coding agents
Orca is the Agent Development Environment (ADE) for shipping with coding agents. Run Claude Code, Codex, Gemini, Cursor CLI, and every other CLI agent in parallel across isolated worktrees. Get work done dramatically faster than any IDE. New features shipped every day. Free, open source, cross-platform.
Continual learning infra for self-improving agents
Meet Sisyphus: The batteries-included agent that codes like you. Multi-model orchestration, Team Mode, background agents, 60+ lifecycle hooks.
Free and open source macOS terminal for AI coding agents. Works with Claude Code, Codex, OpenCode, Gemini CLI, Kiro, Aider, and any CLI tool.
Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.
Open-source Grok Bot alternative. Choose your own model and sandbox.
Open-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.