AI Agents

ICML 2026 | PALM@NeurIPS2026 Oral | Plug-and-play long-term memory for LLM agents

Read-only observability plugin for Hermes Agent: journeys, crossings, guideposts, and reports.

SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution

[NeurIPS 2024] ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution

Calibrated 151M Non-Autoregressive Decision Engine beating TypeSafe Jev & Laya on LocalLLaMA/typed-decisions (77.10% acc, 0.0636 Brier, 0.0144 ECE)

Token 超支？快给史密斯打电话！ Better Call Smith. Adaptive model routing, a glassy Codex usage monitor, and reproducible benchmarks with receipts.

Autumn-Recruit Algo Notes(秋招算法学习仓库)，面向大模型时代的算法、工程与AI学习共建仓库。从数学基础、数据结构，到机器学习、深度学习、LLM、Agent、AI-Infra、语音与数据科学，通过「理解→推导→手写 → 运行 → 验证 → 复盘构建可持续迭代的知识体系。

Camera-only autonomous drone in MuJoCo with a small judgment model (TypeSafe Jev) in the loop at 2.5Hz

An opinionated, curated list of tools for enforcing software development standards: one recommended tool per job, with limits.

Open source autonomous engineering harness in your cloud. One sandbox per task, no real secrets inside.

Claude Code plugin to see, review and iterate on your agent's work without leaving the terminal: show images, play videos, and run visual QA with Playwright recordings and before/after comparisons inside the Claude Code terminal. Works in any terminal that supports the kitty graphics protocol, fully cross-platform on macOS, Linux and Windows.

Neuro-symbolic agents with verified memory. MCP math tools, an algebra repair Skill, and an open challenge. Verify solutions, learn checked rules, and reuse.

One CLI for all your robots. Connect them, command them, and let them work together, each with an LLM for a brain (Claude, OpenAI, Gemini, Grok, or local via Ollama or vLLM), VLAs for arms and decision LLMs (Jev, Laya, Kev). Drives Microduck, Open Duck Mini, LeRobot, XLeRobot, AlohaMini, ToddlerBot, or any ROS 2 base from a laptop, offboard.

学习Agent开发的笔记，尝试让Agent从可用到可靠

Fully Autonomous AI Research System with Self-Evolution, built natively on Claude Code

A bot works with OpenAI GPT models to provide insights for your info flows.

PaperGraph MCP turns math papers into evidence-grounded reading maps for AI agents: extract results, trace proof evidence, plan reading order, and review external dependencies without guessing.

Let your AI agents use your Chrome, signed in as you, in background tabs. By Alexey Indeev · blog: read.aindeev.com · X: @AlexeyIndeev

OrcaReplay — Time travel for AI agents. Record, replay, fork, and debug any agent run with any model. Built by the OrcaRouter.ai team.

Let your AI agents call your phone over VoIP, and call them back. Your phone rings like a real call, even locked; a voice AI talks it through and returns the transcript. Self-hosted, open source, no phone numbers or Twilio.

[ICLR 2025 Oral] This is the official repo for the paper "LLM-SR" on Scientific Equation Discovery and Symbolic Regression with Large Language Models

Broccoli turns Linear tickets into shipped PRs — powered by Claude and Codex, running on your own Google Cloud or Blaxel containers.

All-in-one Web Agent framework for post-training. Start building with a few clicks!

A modular, skill-based autonomous Security Operations Center (SOC) agent that monitors OpenSearch/Elasticsearch data, builds RAG-based behavioral memory, and validates real-time anomalies using LLMs.

Put your idea on trial in front of a jury of 12 Claudes. A free Claude Code skill.

Turn DeepSeek Harness into a self-hosted enterprise Agent platform with knowledge, deep research, content generation, vibe coding, browser automation, governance, and admin controls.

Towards Large Multimodal Models as Visual Foundation Agents

50x your usage with cheap-ag. Opus/Astra plans, a dirt-cheap model writes every line, and tests decide what ships. Your $20 plan stops hitting limits. One MCP server for Claude Code & Codex.

Build your own LLM-native WIKI (knowledge library). Search, extract, summarize, Q&A with contextual RAG, layered knowledge graph, and reinforced memory. Importantly use selected context to automatically generate skills, empowered by Claude subagents + CodeAct pipeline and gated by human review. **Try Live Demo**: https://byo-wiki-demo.vercel.app

The keyboard for the agent era: dictation, copy text from screen, translation, snaps and screen recordings for Claude Code, Codex and your other agents. Free, open source, Mac. 口喷鸡：Agent 时代的输入法。

[NeurIPS'26] Official Implementation for AgentArk: Distilling Multi-Agent Intelligence into a Single LLM Agent(https://arxiv.org/abs/2602.03955)

Supercharge the AI you already use. Greener. Better. Faster. Cheaper.

Deterministic agent harness for Temporal (in Rust)

What The Function: your AI agent decompiles games you own into C that compiles to the exact same bytes. Runs locally.

WikiSkill (arXiv:2608.27454) for Hermes Agent — self-evolving agent skills via a persistent knowledge wiki. Faithful Algorithm 1 implementation with real agent runs, isolated skill gating, and a documented live run log.

Jev DSH 决策引擎｜面向 Agent Harness 的结构化决策插件。原生支持 DeepSeek Harness，通过 iPolloWork 支持 OpenCode、Codex Harness。

Organization-as-Code for autonomous AI agents. Brain-inspired memory that grows, consolidates, and forgets. Multi-model (Claude/Codex/Gemini/Cursor/Ollama).

Agent skill to reverse engineer a SaaS product through the browser into a knowledge base for rebuilding it: screens, rules, data model, design tokens and production barriers, without touching production data.

GRACE (Graph-RAG Anchored Code Engineering): open Agent Skills for contract-driven AI code generation with semantic markup, knowledge graphs, and support for Claude Code, Codex CLI, and Kilo Code.

Fail-closed swarm orchestration with epoch-fenced work and late-completion rejection.

A WorkBuddy-style desktop workspace powered by the DSH plugin ecosystem. WorkDSH manages projects, assets, experts, skills and connectors locally on desktop. All features are extensible via DeepSeek Harness plugins. Local-first, open ecosystem.

Tactical AI Workspace Monitor & EDR

ARTEX 한국어판 ·AI 기반 침해사고 대응 기능 추가 (upstream: Autumn-27/ARTEX, AGPL-3.0)

A living AI-agent office on your desktop wallpaper — Claude Code agents that walk, work, delegate, learn & hold meetings. Per-agent swappable models (Claude/GLM/DeepSeek/Qwen/Kimi/OpenAI/Gemini/Groq/Ollama…), workflows, plugins, voice & Telegram/Discord/LINE. Open source.

把智能体当函数，把想法写成程序。Agent-native functional language with a CLI, Web IDE, goal-driven bots and live UI. Source-available; no AI training.

Spec-driven autonomous engineering workflow for AI coding agents: recon → plan → build → validate → ship — with TDD, adversarial validation, and anti-slop quality gates. Packaged as a Kiro Power.

Autonomous OODA-loop pentesting agent. Hermes brain, Kali + Playwright tools over MCP, ATT&CK as the Orient language.

Evolutionary multi-agent runtime that breeds, evaluates, and improves autonomous agents across reproducible epochs to converge on optimization of a goal.

Jev-Mem: System-One Controlled Agentic Memory

Turn project work into reusable knowledge — an AI-agent skill for Claude Code & Codex