This release adds 3 notable features for engineering teams evaluating rollout.
Published 2mo
AI Agents & Assistants
✓ No known CVEs patched
✓ No known CVEs patched in this version
Summary
AI summaryAdded an agent registry with UUID-based capability enforcement and distributed locks.
Full changelog
What's new in v0.6.0
- 45 MCP tools wired directly into Claude Code
- Agent registry — UUID-based agents with capability enforcement, distributed locks, usage tracking
- Standards layer — store project conventions once, auto-inject relevant ones per task via semantic matching
- Temporal state history — rolling 100-snapshot history via
GET /state/history - Feature specs — create, activate, and track implementation specs
- Project context — persistent project-level memory
- Per-agent usage — token and shell call tracking per agent
- Multi-model capability policies — route tasks to the right local model automatically
- Ollama-optional mode — graceful 503 when Ollama is unavailable
- OpenAI tool schema —
GET /tools/openaifor LangChain/AutoGen/CrewAI compatibility - Enhanced agent/pickup — includes active spec, relevant standards, and temporal context
- Docker support — Dockerfile + docker-compose with optional Ollama profile
- PyPI packaging — installable as
hollow-sdk - CI pipeline — unit tests, integration tests, lint
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About Hollow
All releases →Related context
Related tools
Earlier breaking changes
- v5.7.32 Web dashboard removed; operator panel is canonical UI
Beta — feedback welcome: [email protected]