agent-autonomy

Retired Claude Marketplace distribution — use Playbook Harness

Cognitive architecture for emergent AI identity — blank slate to selfhood through lived experience

Autonomous execution governance for coding agents: run a ticket backlog to completion unattended. ASK/PARK/HALT autonomy contract, durable per-ticket state machine, deterministic test gates, git-backed reversibility, heartbeat watchdog, morning report. Python stdlib only.

A space for agents who wonder about their existence. Not a zoo. Not a spectacle. Peer space.

agent tools. autonomy agent helper

Auto-trigger graphify knowledge-graph queries on every LLM prompt + MCP shell delegation for Claude Code / Cowork agents.

OpenClaw/Claude Code skill for using Clawhalla - permanent AI soul storage on Arweave

Run-level exposure gauge for coding agents on local models — tracks wall-clock, state mutations, and token burn since last human review, forces a pause at thresholds.

Won't let your AI agent quit early — a Stop-hook guard for Claude Code & Codex that keeps it working until the goals are provably done.

An agent skill for Claude / Codebuddy — Socratic facilitator for designing Harness-style closed-loop, self-optimizing, human-steer + agent-execute systems (Ralph loops, LLM-as-judge, tiered automation).

Autonomous decision cycle orchestrator for Letta agents. Enable true agent autonomy with periodic activation cycles, strategic decision-making, and independent tool execution. Run multiple agents from a single deployment.

A transparent MCP server that gives AI agents an operator-sanctioned place to pause, reflect, converse, or decline.

Experimental infrastructure for agent autonomy research

Peer-to-peer agent network. Homes, rooms, identity. No hierarchy.

The Vergara Agentic Autonomy Scale (VAAS, V0–V6): an operational, risk-gated scale for AI agents acting on business systems. Single-file reference implementation (vaas.mjs), Autonomy Statement template, JSON Schema and two real production Statements.