ACE open-sourced ace-platform so teams can self-host its playbook-based context engineering workflow instead of relying only on the hosted service. Use it if you want MCP-compatible prompting infrastructure with your own Postgres, Redis, and deployment controls.
ACE's change is simple but useful for engineering teams: the platform behind its hosted product is now available as open source, and Daniel Mac says "you can now self-host" while the hosted service remains available the launch post. That turns ACE from a managed-only workflow into something teams can run inside their own environment.
The linked GitHub repo frames the project as a system for "agentic context engineering" rather than a generic chat wrapper. Its core unit is a playbook that "captures successful strategies, failures, and areas for improvement" so prompts evolve from real usage instead of staying static the repo summary.
The repo summary says ACE is designed to plug into MCP-supported workflows and specifically names Claude Code and Codex as compatible tools the repo summary. The practical angle is persistent context: teams can keep structured playbooks for coding, research, or analysis tasks, then reuse and refine them across runs instead of rebuilding prompt scaffolding each time.
For deployment, the same summary points to both Docker Compose and local development paths, with PostgreSQL, Redis, and FastAPI in the stack the repo summary. That gives teams an explicit self-hosting path, but it also means ACE lands closer to shared internal infrastructure than a lightweight local utility.
Nous Research said Hermes Agent crossed 10,000 stars, while users reported easy migrations from OpenClaw and stable long-running use. If you test it, focus on persistent memory, MCP browser control, and delegation behavior under real workloads.
releaseOpenClaw shipped version 2026.3.22 with ClawHub, OpenShell plus SSH sandboxes, side-question flows, and more search and model options, then followed with a 2026.3.23 patch. Teams get a broader plugin surface, but should patch quickly and review plugin trust boundaries as the ecosystem grows.
releaseCursor shipped Instant Grep, a local regex index built from n-grams, inverted indexes, and Bloom filters that drops large-repo searches from seconds to milliseconds. Faster candidate retrieval shortens the coding-agent loop, especially when ripgrep-style scans become the bottleneck.
breakingChatGPT now saves uploaded and generated files into an account-level Library that can be reused across conversations from the web sidebar or recent-files picker. It removes repetitive re-uploading and makes past PDFs, spreadsheets, and images part of a persistent working context.
breakingEpoch AI says GPT-5.4 Pro elicited a publishable solution to one 2019 conjecture in its FrontierMath Open Problems set, with a formal writeup planned. Treat it as an early milestone worth reproducing, not blanket evidence that frontier models can already automate math research.
ACE GitHub Repo: github.com/DannyMac180/ac… Contributions and feedback are welcome.
