# Automata

A research project for creating self-improving AI agents through interaction.

## Decision Card

- Recommendation score: 43/100 (Needs evidence)
- Fit score: 61/100
- Trust tier: Needs review
- Install readiness: MCP ready
- Trial status: not_recorded
- Claim status: Unclaimed
- Verified level: Unverified
- Primary risk: Stale source activity
- Next action: collect_evidence

## Fit & Capabilities

- Role: Coding & Development
- Protocols: http, mcp, sdk
- Capabilities: RAG, Multi-agent orchestration, Workflow automation, Coding assistance, Design assistance, Chat interface, Web data extraction, MCP integration

## Evidence

- Source: https://aiagentsdirectory.com/agent/automata
- Source activity: Source review needed
- Community reviews: 0
- External reputation signals: 0
- Known gaps: community review, third-party review/discussion signal, sandbox trial result, high-risk review clearance

## Risk & Safety

- Security verdict: Blocking risk is visible. Do not install or grant credentials until reviewed.
- Required checks: Verify install source, Confirm license, Review permissions, Collect user evaluation

## Installation

- Readiness: MCP ready
- Primary method: MCP template
- Install JSON: https://agentstaffer.com/mcp/aiagentsdirectory-automata/install.json

## Trial Plan

- Task: Run a small code review trial
- Expected output: A concise review with reproducible findings, changed-file scope, and test suggestions.
- Trial JSON: https://agentstaffer.com/mcp/aiagentsdirectory-automata/trial.json

## Profile Data Package

- profile.json: https://agentstaffer.com/mcp/aiagentsdirectory-automata/profile.json
- score.json: https://agentstaffer.com/mcp/aiagentsdirectory-automata/score.json
- evidence.json: https://agentstaffer.com/mcp/aiagentsdirectory-automata/evidence.json
- trust.json: https://agentstaffer.com/mcp/aiagentsdirectory-automata/trust.json
- trial.json: https://agentstaffer.com/mcp/aiagentsdirectory-automata/trial.json
- install.json: https://agentstaffer.com/mcp/aiagentsdirectory-automata/install.json
- history.json: https://agentstaffer.com/mcp/aiagentsdirectory-automata/history.json
- similar.json: https://agentstaffer.com/mcp/aiagentsdirectory-automata/similar.json
- dossier.md: https://agentstaffer.com/mcp/aiagentsdirectory-automata/dossier.md
- summary.md: https://agentstaffer.com/mcp/aiagentsdirectory-automata/summary.md
- mcp.json: https://agentstaffer.com/mcp/aiagentsdirectory-automata/mcp.json
- visibility-report.json: https://agentstaffer.com/vendors/aiagentsdirectory-automata/visibility-report.json
- claim.json: https://agentstaffer.com/claim.json
- Vendor visibility report: https://agentstaffer.com/vendors/aiagentsdirectory-automata/visibility-report
- Agent index: https://agentstaffer.com/agents.json

## Review Notes
- Use profile.json for a compact candidate summary.
- Use install.json before recommending local installation.
- Use score.json to explain the evidence-adjusted recommendation score; fitScore alone is not a hire signal.
- Treat maintainerProfile as verified-owner copy, not as independent scoring or safety evidence.
- Follow agents.json pagination for exhaustive crawling instead of loading many profiles concurrently.

## Risk Signals
- Stale source activity: Last visible update is about 778 days old.
- No community evaluation: AgentStaffer users have not submitted a review yet.
- Third-party reputation pending: Third-party review or discussion signal is pending. Source stars, downloads, likes, and activity are tracked separately as source traction.
- Unknown license: License metadata is missing, so commercial or redistribution rights need manual review.
- Marketplace review note: matches:agent,agents,workflow,automation,mcp,skill