One place where your company's AI skills, tools and knowledge live - centrally managed, reviewed and access-controlled, and usable from any AI agent. Hexis is a layer on top of Git: same core (versioning, PRs), plus a clean UX so anyone can use skills, suggest changes, and submit new ones and admins can govern which context, tools, and skills each person, team, or agent can access. Consumed via MCP, works in any agent in the company.
Loading comments…
Project Info
Product Keywords
Hexis is a central hub where your company's AI skills, tools, and knowledge live—managed, reviewed, and access-controlled in one place, and usable from any AI agent. It's built as a layer on top of Git, so you get the same core you already know (versioning, pull requests) plus a clean interface that makes it easy for anyone to use skills, suggest changes, and submit new ones. Admins govern which context, tools, and skills each person, team, or agent can access. Consumed via MCP (Model Context Protocol), Hexis works with any agent in your company—Claude Code, ChatGPT, Cursor, or any MCP-capable tool.
Everything in Hexis lives in a git repository you own, on any git host—GitHub, GitLab, Bitbucket, Azure DevOps, or self-hosted. Skills are stored as SKILL.md folders, tool manuals use UTCP format, and knowledge is versioned with branches. Every change has an author and a way back, and proposed changes go through owner approval before they land.
Admins decide which context, tools, and skills each person, team, or agent can access. Rules apply to agents exactly as they apply to people—no special exceptions, no loose ends. This keeps sensitive tooling and knowledge locked down while still letting employees work freely within their role.
Agents connect to Hexis through a built-in remote MCP server secured with OAuth 2.1. Employees add the workspace to their agent with a single connection key—no per-tool credentials handed around, no per-agent setup projects. The agent can then use exactly the skills, tools, and knowledge their role allows.
Tool manuals and credentials are protected with an encrypted secrets vault, so sensitive information stays secure even when agents access it. This removes the need to share credentials manually and keeps everything in one governed place.
"The investment lives with you, not inside one vendor's walls."
Hexis is independent of any agent vendor because it speaks open protocols. You can switch agent vendors on price and performance—or mix them by task and role—without rebuilding what your agents know and can do. That vendor independence is what makes enterprise agent rollouts fast: you onboard the next team or the next agent instead of starting over. Combined with the Git-backed core and clean UX, Hexis gives you both control and flexibility in one package.
You're deploying AI agents across a company and want a single, governed place for skills, tools, and knowledge—without locking yourself into one agent vendor. If you value version control, role-based access, and change approval workflows for AI assets, and you want something you can self-host in minutes, Hexis is worth a look. The live demo at demo.bevel.software lets you try the full loop before you commit.
Other tools you might consider
GitHits gives coding agents access to the open-source code your app depends on. Get real implementation examples, dependency source navigation, package inspection and documentation. Agents can grep and read your codebase. They can't grep and read the open-source code your app depends on. That's where they start guessing, retrying, and looping. GitHits builds a version-aware index on demand. Agents can search, navigate, and inspect the code behind their dependencies. CLI: npx githits@latest init
Harness Starter Kit helps teams turn fragile AI coding prompts into durable repository rules: AGENTS.md, drift checks, failure memory, adoption reports, and stack profiles for safer agent collaboration.
Most agents pass their evals and fail in production. Prefactor is the evaluation layer that closes the gap. We score every agent run in real time, surface quality regressions and drift as they happen, and show engineering teams exactly how their agents are performing at scale. Built for the teams shipping agents to customers.
Same AI. 5x the tokens. Coworker provides deep company context and automatically routes to the right model for every task. More chat, cowork and code with the same spend.
Maker
blueprint_b
Loading comments…
