Hexis

One place where your company's AI skills, tools and knowledge live: centrally managed, reviewed and access-controlled, and usable from any AI agent. The open-source core of the Bevel platform.

• Every employee connects once, in minutes. They add the workspace to Claude Code, ChatGPT, Cursor or any MCP-capable agent with a single connection key, and their agent can use exactly the skills, tools and knowledge their role allows. No per-tool credentials handed around, no per-agent setup projects.
• The company stays in control. Skills, tool access and knowledge are managed and reviewed in one place: every change has an author and a way back, and anything proposed through a change request reaches its owners for review before it lands. The rules apply to agents exactly as they apply to people.
• Independent of any agent vendor. Because the workspace 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. The investment lives with you, not inside one vendor's walls. That is what makes enterprise agent rollouts fast: onboard the next team, or the next agent, instead of starting over.

Under the hood, everything lives in a git repository you own, on any git host: skills (SKILL.md folders), tool manuals (UTCP) with an encrypted secrets vault, and knowledge. You get branches, change requests with owner approval, role-based access, and a built-in remote MCP server (OAuth 2.1) that agents connect to.

Contents

• See Hexis in action
• Connect Hexis to Cline
• Try the live demo
• Managed hosting
• Deploy with Docker
• Local development
• Environment reference
• Troubleshooting
• Repository layout

Watch the full walkthrough: connect an agent, use company context, review proposed changes, and manage team access.

See Hexis in action

Propose and approve skill changes

Anyone can propose a new skill or improve an existing one. On protected branches, owners review the exact change and approve it before it becomes available to the team's agents.

Use your team's skills in Claude

Connect Claude to Hexis over MCP, then ask normally. Claude can discover and load the approved skill instructions and company context your role can access, without copying prompts between tools.

Connect Hexis to Cline

Cline can connect directly to Hexis as a remote Streamable HTTP MCP server. Install the public demo connection from the Cline CLI:

cline mcp install hexis --transport http https://demo.bevel.software/api/mcp --yes

Complete the OAuth sign-in in your browser when prompted. Cline then discovers the skills, tools and context your Hexis role can access. For your own Hexis deployment, replace demo.bevel.software with your deployment's host.

Share skills with the right people

Add teammates to roles or grant access directly when needed. Everyone connects to the same workspace, while each person and their agent only sees what they are allowed to read.

Try it first: the live demo

demo.bevel.software is a public instance you can sign into with your Google account, populated with a fictional company's knowledge, skills and tools. The Start here page walks you through the whole loop: connect your own agent over MCP, have it build a sales deck from a skill, watch its proposed improvement arrive as a change request. The demo is shared and read-mostly (visitors propose, owners approve); everything below gets you the same thing with none of the limits.

Want a managed instance?

We run it for you (hosting, upgrades, backups, SSO) and your team just signs in. Write to ali.raza@bevel.software.

Deploy it in 5 minutes (Docker)

You need: Docker with Compose on a server (or your laptop; one line below differs), and an empty git repository on any host (GitHub, GitLab, Bitbucket, Azure DevOps, self-hosted) to hold your knowledge base. The app seeds it with a starter template on first run.

git clone https://github.com/Bevel-Software/Hexis.git
cd Hexis
cp .env.example .env

Open .env and fill in the four required values (everything else can wait):

ADMIN_EMAIL=you@example.com     # the deployment owner, always an admin
ADMIN_PASSWORD=pick-something   # sign-in password; only with password login (SSO-only deployments drop it, see below)
JWT_SECRET=…                    # generate with the command below
SECRETS_ENC_KEY=…               # generate with the command below

Generate the two secrets (run twice, paste one result into each):

node -e "console.log(require('crypto').randomBytes(32).toString('base64'))"
# no Node installed? docker run --rm node:22-slim node -e "console.log(require('crypto').randomBytes(32).toString('base64'))"

For a public deployment, also set the origin values:

PUBLIC_BACKEND_URL=https://bevel.your-domain.com   # public origin; OAuth redirects are built from it
PUBLIC_FRONTEND_URL=https://bevel.your-domain.com  # same origin: the backend serves the SPA

Then start everything (Postgres + the app). Behind a reverse proxy (Coolify, Traefik, nginx; recommended):

docker compose -f docker-compose.yml up -d

Also set TRUST_PROXY to your proxy hop count (1 for a single proxy), so rate limits see real client IPs instead of the proxy's.

The explicit -f skips docker-compose.override.yml, so the app publishes no host port: your proxy reaches it on port 3001 over the compose network. This is deliberate: a fixed published port makes every redeploy fail with port is already allocated, because the replacement container starts while the outgoing one still holds it.

Directly exposed (no proxy): plain docker compose up -d publishes :3001; use APP_PORT=8080 docker compose up -d for a different host port. Leave TRUST_PROXY unset here. With no proxy in front, trusting forwarded headers would let clients spoof their own address.

Open your domain and sign in with ADMIN_EMAIL / ADMIN_PASSWORD.

Just trying it on your laptop? Same steps, minus the origin values: plain docker compose up -d, then open http://localhost:3001.

First sign-in: the setup screen

The app asks for the things it could not guess, and tests them against the real host before saving:

1. Knowledge-base repo: the https clone URL of that empty repository.
2. Git credential: a token with read/write access to it (for GitHub: a fine-grained personal access token with Contents: read & write on that one repo is enough).
3. Branch model: which branch is the default and which are protected (changes to protected branches only land through approved change requests). The repository's real branches are offered as suggestions; for an empty repo the default (main) is fine.

Since the repo is empty, the app initialises it from the bundled template and writes a roles.yaml whose first Admin is you. That's it: you're in the workspace. Head to Skills & Tools to make your first group and skill, and to Connect (in the app menu) to hook up an agent over MCP.

Prefer configuring by environment instead of the setup screen? Every one of those values has an env var (KB_REPO_URL, GIT_TOKEN, DEFAULT_BRANCH, …); anything set in the environment wins over the setup screen. See .env.example.

Worth knowing in production:

• State that survives redeploys: Postgres data plus three app volumes (workspace clones, diff-review backups, tool-chain spill files) are named volumes, so a redeploy or image rebuild loses nothing. Back up the pgdata volume and your knowledge-base git repo; everything else is derivable.
• Health: GET /api/health. First boot can take a minute or two while it runs migrations and seeds the knowledge-base repo.
• Single sign-on: set OIDC_ISSUER_URL / OIDC_CLIENT_ID / OIDC_CLIENT_SECRET (any spec-compliant provider) or configure it on the setup screen, which shows you the redirect URI to register. For SSO-only deployments set LOGIN_PASSWORD=false and drop ADMIN_PASSWORD. If your issuer is multi-tenant (Google, Entra common), set ALLOWED_EMAIL_DOMAINS. SSO auto-provisions accou