AutoBot is the control plane for self-hosted AI. Your data, memory, agents, and knowledge graph live on your infrastructure — pointed at any brain you choose. Run local models today, a frontier API tomorrow. Swap the brain; keep everything you've built.
Free to explore, self-host, modify, and build on — forever. Individuals and hobbyists pay nothing, ever.
Production support & compliance →Docker on a single VM or bare metal. No SaaS, no telemetry. Your documents, memory, and knowledge graph never leave your infrastructure.
The SLM manager controls your AI infrastructure: vector DB, Redis, and which agent uses which provider — local or frontier. Swap providers without losing memory, agents, or knowledge graph.
Start single-node; split frontend, databases, and workers across a distributed fleet — no re-architecture.
All model inference, document storage, and fleet data stays on your servers. No SaaS, no telemetry, no vendor lock-in.
Upload runbooks, man pages, or architecture diagrams. Ask in plain language — AutoBot retrieves and answers from your own indexed content, not training data.
Give the agent a task and let it run: execute shell commands, trigger Ansible playbooks, or chain multi-step operations across your fleet — with confirmation gates.
Add servers from the dashboard. AutoBot generates an SSH key pair, registers the node, and makes it available for remote commands and health checks immediately.
Schedule a weekly health check → summarise → Slack-ready report. Workflows run on cron, trigger on events, or execute on demand with a single click.
Ollama, vLLM, llama.cpp, or any OpenAI-compatible endpoint. AutoBot routes to the fastest available compute — including NPU acceleration via OpenVINO.
FastAPI backend · PostgreSQL/SQLite · Redis · ChromaDB · Ollama. Every component is replaceable, self-hosted, and ships in the Docker Compose bundle.
Vue 3 frontend → FastAPI backend → PostgreSQL / Redis / ChromaDB / Ollama → Ansible / browser worker. Every layer is open source and replaceable.
SLM (Service Lifecycle Manager) is the admin control plane — it handles deployments, health checks, config, and user management separately from chat traffic, so a heavy inference job never blocks an operator command.
Each worker VM has one job and communicates via Redis. Ansible provisions and updates everything — no SSH drift, no manual config. Add a node from the dashboard and it's registered in seconds.
Upload docs once, query forever. ChromaDB stores vector embeddings alongside keyword index. Every system prompt gets your top relevant facts prepended automatically — no retrieval round-trip at chat time.
Start on a single machine. Expand to a full distributed fleet as your workload demands — without changing your workflow.
AutoBot runs on one machine out of the box. Add VMs via the setup wizard and Ansible provisions each role automatically — NPU worker, Redis, AI stack, browser VM.
OpenVINO NPU routing assigns inference tasks to the fastest available compute — Intel NPU, GPU, or CPU — with automatic fallback. No manual routing config.
All four uvicorn backend workers share session cache and rate-limit counters via Redis Stack. Adding more workers requires zero code change.
Every VM role is an Ansible playbook. Push config updates, rotate secrets, or deploy to 20 nodes in one command — no SSH drift.
AutoBot's knowledge base isn't a static FAQ — it's a living, queryable index of everything in your infrastructure: man pages, codebase, documents, and memory extracted from every conversation.
Man pages, source code, internal docs, and PDFs are chunked, embedded with ONNX-accelerated fastembed, and stored in ChromaDB.
Each query runs both dense vector search and BM25 keyword matching, then merges results by relevance score — catching what pure vector search misses.
The top facts about you and your system are condensed into a compact "essential story" block and prepended to every LLM system prompt — no round-trip needed.
After each session, AutoBot extracts durable facts — preferences, project names, infra details — and adds them to memory. The agent improves with use.
ONNX-accelerated embedding generation. No GPU required — the embedding model runs efficiently on CPU with sub-100ms latency per chunk.
Exact-match keyword search complements vector similarity. Critical for queries about specific command names, file paths, or error codes that embeddings can underweight.
LLM-based extraction pulls structured facts from chat history. Content-addressed SHA-256 cache keys ensure stale summaries never outlive their source data.
Context window usage scales automatically to the active model's declared capacity — a 128k-context model uses its full window, not a hardcoded 4k fallback.
One script bootstraps the control plane. The setup wizard walks through fleet configuration.
sudo ./install.sh handles dependencies, SSL, and the initial SLM deploy.
Open the web interface at https://autobot.local and follow the fleet configuration wizard.
All subsequent updates and VM configuration push via Ansible playbooks — no manual SSH required.
# 1. Clone git clone https://github.com/mrveiss/AutoBot-AI cd AutoBot-AI # 2. Bootstrap control plane (~10 min) sudo ./install.sh # 3. Open setup wizard # https://<your-server-ip> # 4. Add fleet VMs in the wizard # NPU worker · Redis · AI stack · Browser # Full fleet ready in ~25 minutes
Every improvement ships faster with fresh eyes. Here's how to get involved.
gh repo fork mrveiss/AutoBot-AI --clone
git checkout -b feature/your-feature origin/Dev_new_gui
Write tests, follow the existing code style, keep commits focused.
Dev_new_gui
Describe what changed and why. CI runs automatically.
Not sure where to start? Browse good-first-issue tags for bite-sized tasks or check open issues for things you care about.
AutoBot is free to run forever. Paid production support is how the project stays funded and maintained. You're paying for our time, guarantees, and compliance work — never for permission to use the software.
Vendor / OEM — reselling AutoBot-as-a-service requires a separate commercial agreement. Contact us to discuss.
Love AutoBot but don't need a support contract? Sponsorships and one-time tips fund the free, open core that individuals and hobbyists use — separate from paid production support.
Recurring or one-time sponsorship through GitHub. Directly funds development time and infrastructure costs.
Support community developmentQuick one-time contribution — buy the developer a coffee. No account needed, any amount appreciated.
Support community developmentThe simplest way to help — star the repo and tell someone who'd find AutoBot useful. Word of mouth matters more than you'd think.
Star on GitHub