Havuz

verl for a single consumer GPU. PPO, GRPO and on-policy distillation on NVIDIA GPUs.

Agentic text-to-SQL SDK: hand the LLM one execute_sql tool and let it explore the schema, test queries, and self-correct — no RAG, no semant

Agent Deck

Drop-in prompt-caching fixes for the LLM agent harness you use. Point your AI coding agent at this repo and it ships the patches.

AI framework for Ruby/Rails developers

Open-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no targ

Official Findings of EMNLP 2026 implementation of Corpus2Skill: compile a document corpus into a navigable skill hierarchy that LLM agents e

Local outcome-loop + reward layer for coding agents — remember what worked, ship the next move, measure how it landed. Docs at nimroboai.com

DeepSeek Harness 的执行迷宫——看 Agent 真实怎么干活：迷宫时间轴 · 数据轨道 · 确定性执行分析 · 多会话对比 | The execution maze for DSH agents: maze timeline, per-step data trac

EurekAgent: an autonomous research system for metric-driven tasks, built with Claude Code. Define the problem and metric. Get breakthrough r

Self-hosted personal AI agent with a WebUI, memory, tools, MCP, sub-agents and automations. Connect local or cloud LLMs.

Use Codex and Claude Code with COMSOL via sim-cli: .mph inspection, live Desktop sessions, bounded execution, artifacts.

VeriFlow-CC: A Claude Code-driven RTL design pipeline. Automates Chip-on-Chat from architecture to synthesis (iVerilog/Yosys) using a statef

Multi-agent research automation framework for LLM agents, with adversarial lab meetings, paper-review rounds, auditable Markdown workflows,

:star: AI-assisted development workflow that produces understanding alongside code. Teach, capture decisions, document, assemble reviews.

Persistent memory system for Coding Agents (Claude, Opencode, Codex), infinite context, learning extraction, persona modeling and so much m

Kit is a coding agent runtime. Claude Code but faster, cheaper and more to the point 🎯

Your own design studio inside the coding agent you already use.

面向 LLM 交易 Agent 的抗污染回测、确定性回放与训练轨迹生成，支持 A 股研究｜Leakage-resistant backtesting, deterministic replay & training trajectory generation for LLM tr

Where agents build agents. An open-source Rust framework for complex agentic systems: ontology-grounded, auditable, one binary.

Pre-inference tool and agent routing for MCP, A2A and tool-rich LLM systems. Reduce candidate tools before model inference with policy-aware

A constitution generator for autonomous, agent-run projects: an interview-driven meta system prompt (and installable skill) that scaffolds a

BuildArena: Physics-grounded Besiege Building for LLMs

Benchmarking data agents for verifiable analytics over heterogeneous workspaces.

Overnight experiment: can an AI agent make money, and can you trust what it reports? The agent produces claims; a separate verifier it canno

PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents

A skill library that teaches Claude Opus the working disciplines of Claude Fable 5. Move the checkpoints, not the capacity.

RimZ is a realtime dashboard and control room for harnessing agentic coding, build on tmux and Zellij.

Audit any agent decision across its past, present, and future, on one typed graph.

AI agent skills for thinking clearly, making better decisions, and getting things done. Strategy, research, decision-making, planning, risk

An opinionated and efficient automated software-factory

The agent that evolves with you 𖤍

STEER — AI4R (AI for Research) experiment framework for auto-research and autonomous research. Connect existing research projects and let an

Decision provenance and data-flow tracking for coding agents: computes what changed in your code and data, records why it changed, and surfa

Agent emotional continuity with PAD state, trust, appraisal, and compact emotion logs.

Token-efficient CLI for Atlassian Server/DC (Jira, Confluence, Bitbucket) — drop-in alternative to mcp-atlassian for LLM agents. Compact out

Model-agnostic output control for LLM agents: concise, action-first answers with proof and risk preserved. Native install paths for Claude C

F.R.I.D.A.Y — a secure self-improving personal AI agent. Local-first, with memory, tools, voice, MCP, automation, and verified self-extensio

AI for tactical cycling intelligence: Predictive mud logic, S-Scale terrain analysis, and powered GPX routing

Portable AI memory powered by knowledge graphs. Transform conversations into a persistent, explorable knowledge graph and give any LLM long-

SimuVerity: Benchmarking Agents for Engineering-Grade Simulink Model Generation

Helix is ​​a powerful self-learning AI agent with memory, skills, and the ability to recall tools. It learns from successful tasks and creat

Open-source, self-hosted AI employees that ask before they act. 46 business roles, approval-gated autonomy, untrusted-content safeguards, sa

Gates 84.7% of tool-schema prompt tokens away for DeepSeek Harness: plugins declare themselves organs, a nerve impulse routes each command,

The agent that learns how you decide - and proves it by never deciding for you. A local-first, loop-native runtime for a team of AI agents o

Local-first, LLM-agnostic memory system — hybrid retrieval (vector + lexical + graph), multi-signal ranking. Runs on 4GB RAM, CPU-only, no c

EMNLP 2026 Industry Track | A benchmark for shopping agents on long-horizon tasks with distributed hidden intent.

Browser-native multi-agent playground: drop LLM personas on a 3D map, watch them live, and talk to them. OpenAI, Gemini, Claude, Ollama. No

OR-Space: a full-lifecycle workspace benchmark for industrial optimization agents

Let Claude run code on your real machine — safely — from any Claude chat. Bridges Claude Cowork to Claude Code on your Mac/Linux box. One co