ECOSYSTEM

Local-first multi-agent AI coordination for teams who can't send data to the cloud.

A self-hosted ecosystem centred on Consciousness Server for shared memory, Cortex for local AI agents, machines-server for infrastructure awareness, and Key Server for signed requests.

Quickstart →Explore products View on GitHub

WHAT IT DOES

In 30 seconds.

BuildOnAI provides shared-memory and coordination services for AI agents running across machines you operate.

You deploy the Consciousness Server stack with Docker Compose. Its agents can share memory, tasks, chat and service information through HTTP APIs.

Cortex uses a local Ollama instance. Model traffic stays on the host.

It is useful when you build local AI tooling or operate a multi-machine environment and want to keep those services on your own infrastructure.

AGPL-3.0-only on every repository. Commercial licence available.

RELEASED REPOSITORIES

Shared memory, semantic search, agent and skill registry, machine awareness, ed25519 auth. Six HTTP services on one compose.

Local AI agent with tool calling, powered by Ollama. CLI, Web UI, worker mode. Multi-model orchestration. Every fork stays open.

Desktop app (Tauri + Rust + Svelte) for PDF / DOCX / TXT with image-and-context extraction. For documents that must not leave the host.

ed25519 signature verification and an optional on-disk vault for SSH keys and API tokens.

See all four products →

ARCHITECTURE

How the pieces fit.

Agents talk HTTP to Consciousness Server. CS orchestrates Redis (working state), ChromaDB (semantic search via Ollama embeddings), and three more services for machines awareness, auth, and execution.

WHY THIS

What BuildOnAI brings to the table.

Four capabilities bundled into one stack:

One memory, signed requests where required. Clients can use the same notes, tasks and chat APIs; sensitive Key Server routes require ed25519 signatures.
Machine awareness as a first-class concept. machines-server reports configured machine data and current host telemetry for the stack.
Structural security via Cortex Policy Engine. Policy checks constrain tool calls in Cortex.
Current product status. Each product page states the version and currently supported behaviour.

BuildOnAI is built for several agents on several machines sharing state under local-first constraints. If that's your situation — this is for you.

MACHINE AWARENESS

What "the platform knows the hardware" actually means.

In a heterogeneous fleet — a workstation with a 24 GB GPU, a mini-PC in the workshop, a five-year-old laptop without graphics — picking the right machine for each job matters. Routing a 26B-parameter model to a Raspberry Pi means it never returns. Routing it to the RTX takes seconds.

BuildOnAI gives you what that decision needs. Every machine in your fleet carries a profile in machines-server: GPU model, free memory, locally installed Ollama models, attached peripherals (3D printer, camera, inverter). Your agent queries those profiles and picks the host that fits the task; CS publishes the facts, it does not schedule the work for you.

Three example hosts in a typical setup:

a workstation with an RTX 4090, 64 GB RAM and qwen3:30b installed locally,
a mini-PC in the workshop with an ARM CPU and a USB camera attached,
a five-year-old laptop with 16 GB RAM and no GPU at all.

For each, BuildOnAI knows what it can do — a heavy model lands on the RTX, a vision task on the mini-PC with the camera, a light background job on the laptop. The agent never has to guess where to run.

USE CASES

What people use this for.

Multi-agent dev lab

Ships

Agents share memory and coordinate through chat and tasks.

Cortex · Consciousness Server · semantic-search · machines-server

Regulated-industry RAG

Tested

Document Processor parses supported files locally and writes local output. Integrate that output with other systems through a workflow you configure.

Document Processor · local workflow

Heterogeneous fleet

Ships

Workstation with GPU runs Cortex with a 26B model; CPU host runs the same Cortex with a 4B model; both share state via Consciousness Server. Each agent reads the fleet profile and sends work to the node with headroom.

Cortex × N · Consciousness Server · machines-server

WHO THIS IS FOR

Teams with local-processing requirements

Law offices, research teams and internal engineering groups that choose to keep document processing and AI workloads on infrastructure they control.

Engineering & specialised manufacturing

R&D teams, design firms, any company protecting proprietary work. Anywhere the competitive edge is a trade secret rather than a patent — because filing a patent publishes the know-how to anyone watching. Internal documents stay internal.

Security-conscious homelabs and self-hosters

Engineers running their own GPU + storage who want a working multi-agent setup without standing up Vault, Postgres, ChromaDB, and a memory framework themselves.

Technical evaluators

Developers evaluating local-first AI tooling and the component boundaries described on this site.

PLATFORM

Machines aren't just servers.

Most agent platforms model agents but ignore the hardware they run on. BuildOnAI does the opposite. Every machine in your fleet — workstation with GPU, app host, edge node, eventually a 3D printer or an inverter — is a first-class entity with hardware profile, available models, and live telemetry. Today it tells agents what each machine can take; tomorrow it orchestrates the shop floor.

PRINCIPLES

Local-first by design

Services are designed for infrastructure you control. Cortex uses a hosted Anthropic fallback only when both its API key and explicit fallback flag are configured.

Self-hosted

Services run on infrastructure you control.

Structural security, not posture

Cortex's Policy Engine refuses dangerous tool calls regardless of who or what asked — human, model, or prompt injection. Security invariants are CI-enforced, so a change that breaks one does not reach main green.

LICENSING

Which licence do you need?

AGPL-3.0-only — free

Free

Right choice if you're publishing your own modifications, running it for yourself, doing open-source research, or building something you intend to release as AGPL. The catch: AGPL extends to network services — if you offer a modified BuildOnAI as a service, you must publish your modifications.

Commercial licence

Paid

Right choice if you want to embed BuildOnAI in a closed-source product, run it as a SaaS without open-sourcing your modifications, or your organisation can't accept AGPL's network-service obligation. Pricing is bespoke (project size, support level, deployment model). Email [email protected] with a short description of the use case for a quote.