axe

by jrswab

A ligthweight cli for running single-purpose AI agents. Define focused agents in TOML, trigger them from anywhere; pipes, git hooks, cron, or the terminal.

Content Signals

Repo Health

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

Trust & Verification

Risk Assessment

• Multi-agent spawning capability: Repository explicitly implements sub-agent delegation and parallel execution of child agents (cfg-subagents.toml, sub-agent-pattern.md)
• Command execution tool: tool-run-cmd.toml indicates agents can execute arbitrary shell commands
• Autonomous operation without approval gates: Agents are triggered via cron, git hooks, CI, and pipes without mandatory human approval checkpoints
• Persistent configuration and memory modification: Supports persistent memory system, memory garbage collection, and agent state storage across runs
• File system manipulation: Agents have write-file, edit-file, and read-file capabilities allowing modification of repository and system files
• External code execution: Multiple test configurations and tool definitions (tool-url-fetch.toml, tool-web-search.toml) indicate network access and content execution