talkie is a vintage language model from 1930

Information hub for our project training the largest possible historical LLMs.

🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.

Open source code for paper "Hista and Numca: Estimate State Value Effectively for Large Language Model Reinforcement Learning"

(ICLR 2026 Oral) Code for the paper: Reducing Belief Deviation in Reinforcement Learning for Active Reasoning of LLM Agents

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini C…

Pre-indexed code knowledge graph, auto syncs on code changes, for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local

An Automated AI Agent Tool for Plotting Your Data in Any Paper's Figure Style.

AI generates a real, editable PowerPoint from any document — native shapes & animations, speaker notes voiced as audio narration, and the option to follow your own .pptx template, not slide images …

From Automated Idea Factory to Realization

Χ-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?

A general framework for strategically scaling evaluation-driven discovery loops, discovering state-of-the-art solutions on 21 open-ended problems.

Causal Inference for the Brave and True的中文翻译版。全部代码基于Python，适用于计量经济学、量化社会学、策略评估等领域。英文版原作者：Matheus Facure

7/24 Office — Self-evolving AI Agent system. 36 tools, 10,000 lines pure Python, modular architecture, MCP plugins, three-layer memory, nudge system, AI mirror, 24/7 production.

Official code for NeurIPS 2025 paper "AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise"

🤖️ A collection of papers, blogs and projects of research agents.

⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA

[NeurIPS 2025 D&B Track] MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research

(ICLR'26 Oral + ICML'26) Learning to Seek and Use Information: Agentic Active Reasoning under Partial Observability

CORAL is a robust, lightweight infrastructure for multi-agent autonomous self-evolution, built for autoresearch. Works with Claude Code, Codex, Cursor, OpenCode, Kiro, and more.

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

A benchmark for evaluating LLMs on open-ended CS problems. Exploring the Next Frontier of Computer Science.

[ICLR 2026] "On the Thinking-Language Modeling Gap in Large Language Models"

[ICLR 2026] "On the Thinking-Language Modeling Gap in Large Language Models"

Official Repo for "EcoGym: Evaluating LLMs for Long-Horizon Plan-and-Execute in Interactive Economies"

This is official github for paper PersonaX