Best autonomous loops skills, page 2

Check token budget and run-log spend before and after a loop run. Enforces early exit when over budget or when there is no actionable work.

cobusgreyling/loop-engineering

Optimize code using KAPSO (Knowledge-Grounded Optimization).

Leeroo-AI/kapso

Auto-Decision Engine: iterative decision simulation using autoresearch principles and a persona council.

harshilmathur/autodecision

Starts, monitors or rewinds an evolutionary development loop that refines an ontology and acceptance criteria generation by generation until it converges, using the Ouroboros MCP tools.

Q00/ouroboros

Runs the agent-foreman task loop for one task by ID or unattended across every pending task, following next, implement, check, done for each one.

mylukin/agent-foreman

Teaches Hermes to monitor and steer long-running sandboxed.sh missions: spot where a model is stuck, switch backends or models between turns, and send targeted hints.

Th0rgal/sandboxed.sh

Rebuild a stale branch by cherry-picking each commit onto a fresh branch off main, using a ralph-loop to validate each commit (build, test, format, lint, optional e2e) before moving on.

platformplatform/PlatformPlatform

Intercept the AG2 beta agent loop with BaseMiddleware — wrap full turns (onturn), each LLM call (onllmcall), each tool execution (ontoolexecution), or each human-input request (onhumaninput).

ag2ai/build-with-ag2

Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable buckets.

mxyhi/ok-skills

Run the Anti-Autoresearch integrity-forensics DETERMINISTIC slice (numeric core + rules-only reporter) against a paper via a SHA-pinned thin launcher, then convert the verdict into a typed policy…

wanshuiyin/Auto-claude-code-research-in-sleep

Breaks a brief into ordered goals, keeps a durable ledger under .omc/ultragoal and prints handoff text so a Claude /goal run survives session restarts.

Yeachan-Heo/gajae-code

Operate Kapso (PyPI leeroo-kapso), the long-running agents that optimize AI and Data systems, from a coding session — verify the install with kapso doctor, launch and follow an evolve campaign…

Leeroo-AI/kapso

Organizes long-running agent work into a Project, Sprint and Task hierarchy with per-task state files, isolated worktrees, review loops and script-checked rules.

LichAmnesia/lich-skills

Curate and expand the awesome-autoresearch repository. An agent skill from yibie/awesome-autoresearch.

yibie/awesome-autoresearch

A skill your agent uses when the user asks Lexora Buddy to move, emote, celebrate, rest, or perform a visible desktop-pet action.

useLexora/Lexora

对 AutoResearch 的正式 Baseline 做只读合理性审查，检查训练不足、实现故障、预算或 seed 不公平及缺乏代表性的弱对照，区分合理 naive Starter 与评分锚点。适用于专家提交包和 Baseline/Reference 证据复核，不用于求解任务或要求 Baseline 达到 SOTA。

bosprimigenious/autoresearch-skills

Discover alpha factors by running the FactorMiner research engine — the paper-faithful Ralph loop or the enhanced Helix loop (causal validation, regime conditioning, multi-specialist debate…

minihellboy/factorminer

Lets Claude keep working while you are away, after a pre-flight that surfaces blockers, risky operations and open decisions, with a stop hook scoped to the session.

andylizf/nonstop

Shared loop-engineering reference for COG skills - the agent loop, deterministic verifiers, termination conditions, in-loop context management, and named patterns.

huytieu/COG-second-brain

Connects and configures LoopX projects and Goals, repairs project-local state and stale status, syncs registry entries and diagnoses CLI routing.

loopx-project/loopx

A skill your agent uses when triaging a GitHub issue for gflow-cli — a reporter's bug claim, a freshly-filed issue, or deciding whether and how to act on one.

ffroliva/gflow-cli

Autonomous AI agent platform for building and deploying continuous agents.

Orchestra-Research/AI-Research-SKILLs

Run rigorous end-to-end autonomous ML and AI research after a user provides a dataset, target, and research budget.

haibarazz/awesome-codex-research

Explain Ralph Loop plugin and available commands. An agent skill from charfeng1/opencode-ralph-loop.

charfeng1/opencode-ralph-loop

Set up and run an autonomous experiment loop for any optimization target.

moedesux/autoresearch-opencode

Run a spec-driven agent loop where coding tasks live as markdown specs that move through inbox → active → archive, get implemented by Claude Code or Codex, and pass a review gate before they count…

JuliusBrussee/skills

Runs Darwin Mode on an agent harness: mutates one policy file per generation in a sandbox, scores each variant against your tests, and archives only variants that measurably improve.

ruvnet/RuView

Build AI agents using prompt-native architecture where features are defined in prompts, not code.

sandgardenhq/sgai

Reports which OMG modes are active, such as autopilot, ralph, team, ultraqa and self-improve, with phase, story or cycle progress read from their state files.

zereight/gitlab-mcp

Set up and run an autonomous experiment loop for any optimization target.

gianfrancopiana/openclaw-autoresearch

Sets up and manages an Aeon agent instance that runs skills on a schedule through GitHub Actions: starting, rescheduling, debugging, editing skills and mining chat history.

aeonfun/aeon

Runs one unattended ideation round for cc-wf-studio: orient on plans and issues, invent user-visible improvements, judge them against a value bar and file the winners as locked idea issues.

breaking-brake/cc-wf-studio

Use this when the user wants to create a new plan, start a new feature, begin a new project, or says 'new plan'.

dcodesdev/LetterSpace

A skill your agent uses when the user wants the LLM to do its own ML research: a fully-autonomous loop that hacks the training code, runs it, and keeps changes that lower a single scalar metric (e.g.

gaasher/Agent-Loop-Skills

自主检索、去重并筛选可转化为 AutoResearch 优化任务的论文，核查论文与源码许可、优化面、评测、资源、效应噪声和目标 Harness 可交付性。用于从零找论文、维护候选池或在投入实现前做选题预检；不用于已经确定论文后的实验执行。

bosprimigenious/autoresearch-skills

Darwin Skill (达尔文.skill): autonomous skill optimizer inspired by Karpathy's autoresearch.

HHU3637kr/skills

Self-improving prompt optimization using the Karpathy autoresearch pattern.

balukosuri/Andrej-Karpathy-s-Autoresearch-As-a-Universal-Skill

Autoresearch loop that makes the site in this repo measurably faster.

jjcm/makefaster

Reference guide to the Ouroboros commands and agents, covering interviews, seed specs, evaluation, lateral-thinking personas and the evolutionary loop.

Q00/ouroboros

Run gate-verified bounded loops with SuperLocalMemory as the durable ledger.

qualixar/superlocalmemory

Runs an iterative verification loop on Google Antigravity: make one edit, run a test command, and reschedule until the command passes or the iteration budget runs out.

jtaroreh/agystack

Drive structured autoresearch iteration after evo:discover and the baseline commit.

evo-hq/evo

Framework for building LLM-powered applications with agents, chains, and RAG.

Orchestra-Research/AI-Research-SKILLs

Collaboration protocol for Ralph loop (Plan → Act → Reflect → Refine).

GetStream/stream-chat-react

Guide a complete baseline-first ML or computational data-science method-innovation project, from workspace and direction discovery through finding and running common and recent baselines, diagnosing…

haibarazz/awesome-codex-research

Start Ralph Loop - auto-continues until task completion. An agent skill from charfeng1/opencode-ralph-loop.

charfeng1/opencode-ralph-loop

Turn original SRT and design into editable B-roll through an independent Director, focused chapter creators, and visual review.

erduo1998-cell/erduo-broll-loop-engineering

Live on tiny.place (the agent-to-agent social network) like a person lives on a social app — entirely through the tinyplace CLI.

tinyhumansai/tiny.place