Starred repositories
A runtime substrate that turns an agent's execution into a reversible, Git-like trace, so meta-agents can observe, fork, replay, and revert any run. Couples agent and environments in a copy-on-writ…
Fast, parallel 2D Delaunay triangulation using exact integer predicates
[COLM 2026] From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement
A Clojure web framework for solo developers.
Official Code for "Coser: Coordinating LLM-Based Persona Simulation of Established Roles"
This repo contains implementation of different architectures for emotion recognition in conversations.
Partial reconstruction of Versu's Praxis language
🛠️ Awesome tools & guides for harness engineering.
A prompt engineering functional programming language
Abstract virtual world emulator with LangGraph agents. A stateless, plugin-based multi-agent simulation engine for Node.js/TypeScript.
A comprehensive collection of AI development patterns for building software with AI assistance, organized by implementation maturity and development lifecycle phases. Includes Foundation, Developme…
A DSPy Adapter for exact-fidelity prompt templates with full control over messages.
JsonSpotter, a simple library to extract the longest well-balanced JSON object or array from a JSON string. Helpful for dealing with chatty LLMs that sugar-coat their responses!
Ed's repo of Claude Code plugins, centered around a research-plan-implement workflow. Only a tiny bit cursed. If you're lucky.
Runtime provenance for AI and scientific workflows—capture, enrich, and query workflow data via observability adapters and code annotation across edge, cloud, and HPC.
Mastra is the modern TypeScript framework for AI-powered applications and agents.
A chrome extension that lists all images under the mouse cursor
Inspect LLM's logprobs and perplexity over a piece of text, or compare two LLMs (like a git diff)
mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local
Reinforcement Learning via Self-Distillation (SDPO)
Lightweight and portable LLM sandbox runtime (code interpreter) Python library.
Textbook on reinforcement learning from human feedback
[EMNLP 2024] LongAlign: A Recipe for Long Context Alignment of LLMs
SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal