# Show HN: Hexis, open-source Claude Skills management

> Source: <https://github.com/Bevel-Software/Hexis>
> Published: 2026-08-14 16:14:19+00:00

**Git-backed control plane for AI-agent skills, tools, context, permissions and
identity. Self-hosted and MCP-native.**

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

One place where engineers and non-technical people alike can browse and load plugins, propose suggestions, and manage access.

Every skill, tool manual and permission is a file in a git repository you own, so the audit trail is the storage layer: who changed what, when, who approved it, and how to undo it. An agent can only do what the person running it can do, resolved per file, and it never holds the credentials it uses. Runs on your infrastructure, behind your own SSO.

A gateway decides which tools an agent may call. It has no opinion on whether the skill telling that agent what to do is any good.

In Hexis, skills and tool manuals are reviewable files. Anyone can propose a change; on protected branches it reaches the owners of the files it touches and ships only once they approve. Agents propose too: one that hits a broken skill mid-task can suggest the fix, and a person decides whether it lands.

[See Hexis in action](#see-hexis-in-action)[Connect Hexis to Cline](#connect-hexis-to-cline)[Try the live demo](#try-it-first-the-live-demo)[Managed hosting](#want-a-managed-instance)[Deploy with Docker](#deploy-it-in-5-minutes-docker)[Local development](#local-development-run-from-source)[Configuration reference](/Bevel-Software/Hexis/blob/main/docs/configuration.md)[Troubleshooting](/Bevel-Software/Hexis/blob/main/docs/troubleshooting.md)[Repository layout](#repository-layout)[FAQ](#faq)

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

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.

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.

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.

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.

** 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.

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

You need: [Docker](https://docs.docker.com/get-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)
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):

``` js
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**.

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

**Knowledge-base repo**: the https clone URL of that empty repository.** 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).**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 plugin and skill, and to
**Connect** (in the app menu) to hook up an agent over MCP.

Going to production? [Configuration reference](/Bevel-Software/Hexis/blob/main/docs/configuration.md) covers
single sign-on, the state you need to back up, health checks, and configuring
by environment instead of the setup screen.

You need: **Node 22** (`.nvmrc`

; the engine range is `>=22 <23`

),
**pnpm 10**, **git ≥ 2.41**, and a Postgres 17 (the bundled one is fine):

```
docker compose up -d db        # just the database
pnpm install
pnpm build                     # builds the packages the apps import
cp .env.example .env           # fill the same four required values;
                               # the default DATABASE_URL already points at the bundled db
pnpm dev                       # backend on :3001, Vite dev server on :5173
```

Open ** http://localhost:5173** (the dev server proxies to the backend). Useful
commands:

`pnpm test`

, `pnpm typecheck`

, `pnpm lint`

.Migrations run automatically on boot; there is no separate migrate step, in dev or in production.

: every environment variable, SSO setup, secret generation, backups and health.[Configuration](/Bevel-Software/Hexis/blob/main/docs/configuration.md): the failures you are most likely to hit, and what causes them.[Troubleshooting](/Bevel-Software/Hexis/blob/main/docs/troubleshooting.md)

| Path | What it is |
|---|---|
`packages/shared` |
`@bevel-software/platform-shared` : shared types + pure domain utilities |
`packages/core-backend` |
`@bevel-software/platform-core-backend` : the core backend (ships `migrations/` + `kb-template/` ) |
`packages/core-frontend` |
`@bevel-software/platform-core-frontend` : the core UI, published as raw TS/TSX source |
`apps/server` |
standalone core backend shell |
`apps/web` |
standalone core SPA shell (Vite) |

Questions that come up when teams evaluate Hexis as a central, versioned catalogue for agent skills and tools.

**How do agents find skills without flooding the context window?**

They look them up rather than loading them all: `list_skills`

and `search`

narrow the field, `get_skill`

returns one skill at call time.

**Which agents can connect?**

Any MCP-capable client, including Claude Code, Codex, Cursor, Cline and ChatGPT, each seeing only what its user's role allows.

**How is the catalogue versioned?**

By git: every save is a commit, so history, blame and revert work as they do for code, and changes to protected branches ship as reviewable change requests.

**What governance do we get?**

Per-file access control, review-gated change requests, and a git audit trail of who changed what and who approved it.

License: [Apache-2.0](/Bevel-Software/Hexis/blob/main/LICENSE)