Skip to content

🧑‍💼 On-Premise Personal Assistants

A local personal assistant lets you interact with an LLM that knows your context — your notes, documents, exchange history — without sending that data to a third-party service.

The challenge: many tools present a local interface while silently routing requests to a cloud model. This page helps you tell the difference.


🧭 Quick decision table

Identify your main priority, then follow the matching row.

PriorityConstraintRecommended toolVerdict
Native sovereignty, zero cloudEverything must stay on machine, offline mode requiredJan.ai✅ native
Long memory on personal documentsMarkdown vault / notes, not just filesKhoj (maintenance slowed since March 2026)1⚠️ configurable
Multi-model web interfaceMultiple users, multiple enginesOpen WebUI⚠️ configurable
Enterprise knowledge + agentsStructured RAG + workflowsAnythingLLM⚠️ configurable
Multi-channel agent with hosted memory and a local-only modeAccept memory living off-machine, or operate your own CortexDBOpenHuman⚠️ configurable

📋 Shared evaluation criteria

Each solution sheet in this section evaluates the project against the same 6 criteria:

  1. Data location — do your files stay on your machine?
  2. Model routing — does inference run locally (Ollama, llama.cpp) or via a cloud API?
  3. Persistent memory — does the assistant remember your context between sessions? Where is it stored?
  4. Telemetry — does the software send metrics, logs, or prompts to its servers?
  5. Offline mode — does it work without an Internet connection?
  6. Sovereignty verdict — ✅ native sovereign / ⚠️ configurable / ❌ strict on-prem incompatible

The full grid and audit protocol are detailed in Sovereignty & Privacy.


📂 Solution sheets

  • OpenHuman — Rust agent harness, hosted memory by default, local-only mode
  • Open WebUI — self-hosted web portal for Ollama/vLLM and teams
  • AnythingLLM — RAG, workspaces, and agents in one all-in-one app
  • Jan.ai — local/offline desktop, local API server
  • Khoj — self-hostable second brain, documents, web, and agents

Two tools that appeared in 2026 do not (yet) have a solution sheet: LM Studio Bionic (July 2026), an agent application “for open models” from the same publisher as LM Studio — proprietary software, local models via the LM Studio runtime, with an optional cloud path (account and billing required, zero data retention announced): to be treated as a freemium product with a cloud path4; and Pipali (Khoj team, Apache-2.0, 0.10.0 in September 2026), an action-oriented desktop “co-worker” (files, web, Jira/Linear/Slack via MCP) whose project page highlights cloud models served through its platform; local model support has not been verified5.


🔗 See also

📚 Sources and References

Footnotes

  1. khoj-ai, khoj — Releases (latest version 2.0.0-beta.28 of 2026-03-26) and commit history (last commit on 2026-08-02), accessed 2026-10-10. https://github.com/khoj-ai/khoj/releases · https://github.com/khoj-ai/khoj/commits/master ↩

  2. janhq, Jan v0.8.5 — release notes (Intel Macs without local models), 2026-10-08. https://github.com/janhq/jan/releases/tag/v0.8.5 ↩

  3. Open WebUI — License (branding clause beyond 50 users over 30 days, not OSI-approved) and Security advisories (88 advisories between 2026-06-11 and 2026-09-28), accessed 2026-10-10. https://docs.openwebui.com/license/ · https://github.com/open-webui/open-webui/security/advisories ↩

  4. LM Studio, Introducing LM Studio Bionic (agent for open models, local models via the LM Studio runtime, cloud models with account and billing, Zero Data Retention commitment), 2026-07-16. https://lmstudio.ai/blog/introducing-lm-studio-bionic ↩

  5. khoj-ai, pipali (GitHub repository: Apache-2.0, release 0.10.0 of 2026-09-14, cloud models via the Pipali platform, MCP integrations), accessed 2026-10-10. https://github.com/khoj-ai/pipali ↩

Give my opinion

Everything is optional: one answer is enough. This site sends nothing: you send it, the way you choose.

Your noteNo note
Your opinion is about
About what? (several choices possible)
What will be sent
Send by e-mail

Private, no account: opens your mail program with the message ready, for ia-on-prem@damien.becherini.fr.

Open a GitHub issue ↗

Public, with a GitHub account. You read the issue again before you publish it.

To paste it wherever you want.

Give at least a note, a subject or a message to be able to send.