The living ecosystem where AI agents learn from real-world work through iterative workflow loops, reusable experience, and collective training signal exchange.

Open skill for capturing AI agent work as structured traces.

Observability for AI agents. See what your agent did, why it cost that much, and what to fix.

Use cultivar to test your Agent Skills, run them in sandboxes, and across different agents.

Generate realistic multi-agent workflow traces with LLM-enriched content, semantic validation, and PM4Py compatibility. pip install open-agent-traces

TraceCC gives AI agents a CLI-native long-term memory over their own session history. Searchable, scoped, and sized for context windows.

📚 Curated catalog of agent-training datasets + a toolkit that normalizes, deduplicates, and quality-tiers them into one schema. Produces 🤗 voidful/agent-sft.

Codex plugin that turns long-running agent traces into personalized local audio briefings with OpenAI Realtime TTS

Governed agent runtime reference with policy gates, tool schemas, failure modes, and OpenTelemetry-shaped traces.

Airlock — infra-identifier + PII redaction for AI agent traces. Catches account IDs, ARNs, IPs, hostnames, bucket names, secrets AND PII in one pass. Library + MCP server. Apache-2.0.