Skip to content

Auctalis/nocturnusai

v0.3.11 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agentic-ai agents ai-agents ai-memory backward-chaining context-engineering
+8 more
cost-optimization inference-engine knowledge-graph langchain logic-programming mcp reasoning truth-maintenance

Summary

AI summary

Adds the standalone MCP stdio server package nocturnusai-mcp and a live benchmark suite.

Full changelog

Adds the standalone MCP stdio server package (nocturnusai-mcp on npm) and the live benchmark suite.

🚀 New

  • nocturnusai-mcp npm package — MCP stdio shim that bridges any MCP-compatible client (Claude Desktop, Cursor, Windsurf) to a running NocturnusAI server. Published on npm as [email protected]. See sdks/mcp-server/README.md.
  • nocturnusai-bench — Live benchmark runner measuring token savings, turn reduction, and cost impact against real LLM workloads.
  • Benchmark page/benchmark on the docs site with live results.

📊 Site

  • Grounded all token/cost claims in live benchmark results
  • Added /calculations page with methodology transparency
  • Consolidated navbar into Product + Proof dropdowns
  • Added /about page
  • SEO essentials: sitemap, RSS, OG, JSON-LD, blog covers

🔧 Infra

  • Docker build now receives clean semver VERSION build-arg
  • BUSL-1.1 license metadata made discoverable to automated scanners
  • Locked versioning to 0.3.x series per maintainer policy

All 764 tests pass.

Full diff: https://github.com/Auctalis/nocturnusai/compare/v0.3.8...v0.3.11

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

Track Auctalis/nocturnusai

Get notified when new releases ship.

Sign up free

About Auctalis/nocturnusai

Deterministic reasoning engine for AI agent context compression. Extracts structured facts with logical inference, proof chains, and truth maintenance. REST API, Python/TypeScript SDKs, and MCP server integration.

All releases →

Related context

Beta — feedback welcome: [email protected]