Dev & Engineering markdown-skillsml-researchcross-model-reviewcodex-clianti-autoresearchresearch-automation

ARIS ⚔️🌙 Auto-Research-In-Sleep

Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation.

FollowAgents review · FARS-2.1
Not recommended
45/ 100 5-point scale 2.3 / 5
1 2 3 4 5 6
1Trust10 / 29 · 1.7/5

Evidence shows the repository contains multiple components (e.g., llm-chat, feishu-bridge) that require API keys and network access, but least privilege or user confirmation mechanisms are not clearly stated. Data flow transparency is limited; sensitive data handling (e.g., API keys) is mentioned but not detailed. Dependency security is not fully assessed; external effects (e.g., network calls) exist but are not explicitly controlled. Rollback mechanisms are not mentioned. Source attribution is partially clear (e.g., MIT license, author info) but unverified.

2Reliability6 / 14 · 2.1/5

Internal consistency is good; README and code structure are largely aligned, but dependency availability is not explicit (e.g., requires external API keys). Failure messages have some examples (e.g., error handling) but are not comprehensive.

3Adaptability9 / 18 · 2.5/5

Target audience is clear (AI researchers, developers), scenarios are diverse (research automation, interview prep, etc.). Capability boundaries are partially described (e.g., skill list), but trigger precision (e.g., skill trigger conditions) is not detailed. Environment fit is good (supports multiple CLIs and OS).

4Convention10 / 18 · 2.8/5

Information architecture is clear (README, docs, skills directories), install notes exist (e.g., ARIS-Code CLI installation), naming stability is moderate (frequent version updates), examples and FAQ are provided, known limitations are partially mentioned (e.g., output folding), license is clear (MIT), versioning/changelog is detailed, maintenance responsibility is partially clear (author and contributors).

5Effectiveness7 / 13 · 2.7/5

Output usability is good (e.g., generates reports, HTML), marginal value is high (automates research workflow), cost-benefit is not fully assessed (e.g., API costs).

6Verifiability3 / 8 · 1.9/5

Claim traceability is moderate (e.g., technical report link), cross-source corroboration is limited (e.g., external recommendations), fact-inference separation is unclear.

Evidence confidence: Low Reviewed Aug 09, 2026 Reviewed revision e3aa6f83b09d
The upstream repository has new commits since this review. The score still applies to the reviewed revision shown and may not cover the latest changes.
Before you use it
  • The repository contains components that require API keys; ensure secure storage to avoid leakage.
  • Dependencies on external services (e.g., OpenAI, Feishu) may incur network and cost implications.
  • Frequent version updates; monitor changelog for behavior changes.
Review evidence [1][2][3][4][5][6]
See the full review method →

What does this agent do, and when should you use it?

ARIS is a lightweight, Markdown-only skillset for autonomous ML research. It orchestrates cross-model collaboration: Claude Code drives the research while an external LLM (via Codex MCP) acts as a critical reviewer. Its core methodology is an adversarial review loop to break single-model blind spots. The skill layer is transportable across Claude Code, Codex CLI, Cursor, Trae, Antigravity, and GitHub Copilot CLI. It is also packaged as a standalone ARIS-Code CLI (Rust) providing a REPL, MCP tool dispatch, no-API-key cross-model reviewing, and a bundled skillset. The repo includes 81 skills, 13 named workflows, and extension projects like Anti-Autoresearch integrity forensics and ARIS-Movie-Director. Licensed MIT.

It provides a collection of skills as plain Markdown, each defining a step of autonomous research: idea generation (/research-idea), literature review (/research-lit), paper writing (/paper-writing), experiment design (/experiment-bridge), and post-acceptance tasks like slides generation (/paper-slides) and rebuttal (/rebuttal). The core mechanism is cross-model review: Claude Code executes, while another model (via Codex MCP or LLM API) audits the output. Skills are composable into pipelines, such as /research-pipeline, which takes a research direction, reads reference papers, clones repos, generates ideas, runs experiments, and writes the paper. The standalone ARIS-Code CLI offers a REPL (/plan mode, /tasks persistent tracking), tool calls, MCP server integration, and auto-setup with bundled skills. It also includes a Research Wiki for persistent note-taking across sessions.

  1. An ML researcher who wants automated research idea generation, experiment running, and paper drafting overnight, waking up to a scored paper.
  2. A graduate student with a paper draft and reviews who needs a structured rebuttal within character limits with fabrication safeguards.
  3. A researcher with a codebase and an idea who wants to automate the full improvement pipeline using /research-pipeline.
  4. A team that wants to use cross-model adversarial review to avoid single-model blind spots, with Claude + Codex or alternative model pairs.
  5. A developer who wants to bring the same skill workflows to non-Claude environments: Codex CLI, Cursor, Trae, or other SKILL.md-compatible agents.
  6. An educator or author who wants to collaboratively write teaching materials or structured documents with cross-review using /render-html.

What are this agent's strengths and limitations?

Pros
  • Cross-model review breaks self-play blind spots: two models (speed × rigor) yield better outcomes than a single model talking to itself
  • Fully transportable: plain Markdown SKILL.md files can move between Claude Code, Codex CLI, Cursor, Trae, Copilot CLI, etc., with zero lock-in
  • Built-in rebuttal safety gates: /rebuttal has no-fabrication, no-overpromise, and full-coverage guarantees
  • No-API-key cross-model reviewing: via Codex MCP with ChatGPT subscription, you can have a reviewer without an OpenAI API key (or use alternative models like Kimi, DeepSeek)
  • Active development with transparency: detailed changelogs referencing real user issues, and frequent releases
Limitations
  • Steep learning curve: multiple workflows, skills, and configuration options may overwhelm beginners
  • Relies on external model APIs: ensuring reliability requires API credentials or multiple providers; cost can vary with plans
  • Potential for hallucinations like any AI tool: despite safeguards, outputs need human verification, especially for critical research
  • Requires a compatible agent runtime: although not locked in, it needs a SKILL.md-compatible agent like Claude Code or Codex CLI

How do you install or deploy this agent?

There are several installation paths:

  1. Lightweight skills: clone the repo and run bash tools/install_skills.sh (or the relevant installer for your agent, e.g., install_skills_codex.sh). The installer copies skills to ~/.claude/skills or ~/.config/codex/skills.
  2. Standalone CLI: download the latest ARIS-Code binary from the releases page, or build from source (requires Rust). Run aris setup to configure provider and model.
  3. Via script: bash tools/smart_update.sh --apply to pull updates. For selective install, use --groups X,Y or --skills X flags.

How do you use this agent?

For skills: start in Claude Code, invoke /research-pipeline "research direction" for the full pipeline, or individual skills like /research-idea, /research-lit, /paper-writing. Cross-model review requires configuring a second model: via aris setup (option 10: Codex MCP uses ChatGPT subscription, no API key) or with OpenAI/Anthropic API keys. For the ARIS-Code CLI: run aris "your prompt" or aris to start a REPL. Use /plan for planning, /tasks for tracking tasks, /research-wiki for persistent memory.

How does this agent compare with similar options?

It is compared to Anthropic's Claude Science skills and OpenAI's Codex CLI native skills. It encourages use with Codex CLI over Claude Code for greater model flexibility. It distinguishes itself from commercial tools like 'ChatGPT autopilot research' by emphasizing its lock-in-free approach.

FAQ

What is the cost of using ARIS?
The skills are free (MIT), but you need model access: Claude via API or subscription, GPT via OpenAI API or ChatGPT subscription (through Codex MCP). ARIS supports multiple models, so you can choose the most cost-effective option.
Under what permissions does ARIS run?
It runs as a local skill or CLI with access to your filesystem, shell, and network, as configured by you. For the CLI, there is an approval mode (PermissionMode::Prompt) that prompts for approval by default, though an earlier version silently allowed everything in prompt mode (fixed in v0.4.6). When using MCP tools, you approve them.
How does ARIS handle failures and errors?
It includes retry logic, stream timeouts, MCP protocol version validation, and regression tests. It also has guardrails against fabricating results and uses cross-model review to catch errors. However, as with any automated system, you should verify critical outputs.
Is ARIS for general writing or only research?
While focused on research, it has expanded to non-academic research (ARIS-Anything) and education (ARIS-in-AI-Offer). The core methodology (plan-draft-review-iterate-persist) is general and can be applied to investing, legal, and other fields.

Compare agents like this one

The same FARS review applied across the shortlist this agent qualifies for.

Related agents