Stars
A Unified Memory Benchmark Suite for Memory-Augmented Agents
Automatically message copilot cli to keep going whenever it stops (useful for autoresearch loops).
Enterprise-grade (40m+ LOC) codebase intelligence, zero-setup, local & private Plugin/Skill/Extension or MCP: hybrid semantic search, polyglot dependency graphs, symbol-level impact analysis & call…
Let the agent write the weights, why not?
Python SDK for ProgramAsWeights — compile natural language specs into neural programs that run locally
[ACL2025 Oral] Cuckoo: A Series of IE Free Riders Using LLM's Resources to Scale up Themselves.
🦞 Just talk to your agent — it learns and EVOLVES 🧬.
Framework for evaluating and improving agents
Dataset and benchmark for RAG on company internal documents.
Skills for Real Engineers. Straight from my .agents directory.
A trainable Belief Rule-Based (BRB) inference system with an sklearn-compatible API and optional JAX backend for differentiable training.
Context window optimization for AI coding agents. Sandboxes tool output (98% reduction), persists session memory, and enforces routing across 17 platforms via MCP + hooks.
AI agents running research on single-GPU nanochat training automatically
Agent-interpretable data-science tools, evolved via autoresearch.
"Vibe-Trading: Your Personal Trading Agent"
Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞
A curated collection of research on tabular foundation models: models pretrained on large-scale (synthetic) data that generalize to unseen tabular tasks at inference time.
Repo for Paper: Discovering Interpretable Algorithms by Decompiling Transformers to RASP
A carefully curated collection of high-quality libraries, projects, tutorials, research papers, and other essential resources focused on Mechanistic Interpretability, a growing subfield in machine …
A Playground for Tabular Foundation Models
Interpretable Causal Diffusion Language Models
Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
CyberBench: A Multi-Task Cyber LLM Benchmark