The projects

Use one on its own, or run them together. Each is a complete product with its own repository, documentation and Docker setup — and pacod-demo runs all six as one platform.

pacod-gw

AI gateway. One gateway in front of every model — with the keys, prices, quotas and usage your applications should not have to hold.

pacod-gw sits between your applications and the LLM providers. A Rust core relays or translates every call, keeps provider keys out of your apps, enforces limits, prices each request and can answer a repeated call from its cache. Usage flows into ClickHouse analytics, and everything is managed from a SvelteKit console.

pacod-cms

Content management. One stack, many editorial websites — articles, advertising and statistics, with AI writing, design and translation built in.

pacod-cms is an open-source content management system for editorial websites. One installation hosts many sites, each with its own database, files and cache; editors work in a multilingual studio, and readers get fast, host-routed public sites.

pacod-ap

Agent-building platform. Host any number of AI agents on one deployment — each with its own knowledge, facts, prompts and rules, behind one sign-in.

pacod-ap hosts any number of self-contained AI agents on one deployment. Each agent answers from its own knowledge base and exact reference facts, cites its sources and is reviewed from its own conversations; all of them share one sign-in through pacod-id, one admin console and one LLM gateway, pacod-gw.

pacod-id

Identity and access. One place where people and machines sign in — and where it is recorded what they may do, across all your products.

pacod-id is the OpenID Connect provider behind the PACOD products: one pool of accounts, hosted sign-in and account pages, organisations and role bindings. Its tokens say who someone is, not what they may do: each product follows a feed of the role bindings and decides access itself, with one rules engine written in Rust, TypeScript and Python.

pacod-kb

RAG knowledge base. Turn files and web pages into versioned, searchable knowledge — with a stable contract for the models that read it.

pacod-kb ingests files and web pages, converts them to canonical Markdown, indexes them for hybrid semantic and keyword search and keeps every version. It scans each document for prompt injection before anything is indexed, and hands downstream models passages they can cite, under a documented metadata contract. It runs on CPU, and searches stay responsive while documents are being ingested.

pacod-benchmark

Gateway benchmarks. Measure what the gateway adds — in many configurations at once, each against a baseline straight to the mock.

pacod-benchmark measures pacod-gw (its managed and proxy modes, the minimal gateway, its deployment layouts) and other gateways, in many configurations in one run. Every cell is measured against a baseline that calls the mock provider directly, so what is left is what the gateway added. Its UI writes the suites, follows the runs second by second and compares them; the reports go to the gateway's console.

pacod-demo

The whole stack. All six projects working as one platform — one domain, one sign-in, one gateway. Try it at demo.pacod.io.

pacod-demo runs identity, the AI gateway, the agent platform, the CMS, the knowledge base and the gateway's benchmarks together on one machine, from one configuration file and one make. It includes each repository's own compose file unchanged, shares one of each common component between them, introduces the products to each other and checks that they work as one; every night it goes back to a known state.