Khoj
Open-source, self-hosted personal AI over your own documents, with custom agents, scheduled research automations and local model support. Hosted cloud sunset April 2026.
Khoj is an open-source personal AI, often described as a self-hostable second brain. It lets a person chat with any local or online LLM, get grounded answers from the web and from their own documents (PDFs, Markdown, Notion, Word, org-mode, and more), and reach it from the browser, desktop, phone, Obsidian, Emacs, or WhatsApp.
Beyond retrieval and semantic search, Khoj is genuinely agentic. Users can build custom agents with their own knowledge, persona, chat model, and tools, schedule automations for recurring research and notifications, run an autonomous deep-research mode, and execute code in a sandbox. It is model-agnostic across providers such as GPT, Claude, Gemini, Llama, Qwen, and Mistral.
Importantly, the product's footprint has changed. Khoj Cloud, the hosted service at app.khoj.dev, was sunset on April 15, 2026. The project itself remains fully open-source under the AGPL-3.0 license and self-hostable, with active development continuing on GitHub. The team behind it, Khoj AI (a Y Combinator company), has shifted its focus to two newer products. Pipali is an open-source AI coworker that runs locally and can read and write files, use the browser, run code in a sandbox, and integrate with tools like Jira, Linear, and Slack over MCP. Open Paper is a research assistant for literature review.
For teams evaluating it today, Khoj is best understood as a mature, self-hostable open-source personal-AI project rather than a managed cloud service, with the company's newest energy going into Pipali and Open Paper.
Vendor details
Canonical URL
https://khoj.dev
Category
Agent builder
Subcategory
Self-hosted personal AI over your own documents, with custom agents and scheduled research
Funding status
Independent. Khoj AI is a Y Combinator company (W24). The khoj project is AGPL-3.0 open source at roughly 36,700 stars and 2,400 forks, with commits continuing into August 2026. Khoj Cloud, the hosted service, was sunset on 15 April 2026 and the company's active development has shifted to two newer products, Pipali and Open Paper.
Company status
independent
Use cases & customers
Primary use cases
Deployment options
Integrations
Khoj indexes the customer's own documents across PDF, Markdown, org-mode, Word, Notion files and images, with local files and folders kept continuously synced by the desktop, Obsidian and Emacs clients and a Notion workspace synced from the web app. Agents are given tools including web search and a Python code-execution sandbox. Chat models are configured per provider through an AI Model Api object covering OpenAI, Anthropic and Gemini, plus offline and local models through any OpenAI-compatible server including Ollama, vLLM, LMStudio and llama-cpp-server, with separate Default and Advanced model settings governing intermediate steps such as intent detection and web search. Client surfaces are the web app, desktop, Obsidian, Emacs, phone and WhatsApp, with delivery of scheduled research and notifications to email. There is no catalog of third-party application connectors for acting on external systems, and there is no API reference.
In practice
You want to ask questions across your own notes and documents without handing them to a cloud vendor. Khoj runs self-hosted and gives grounded answers from your PDFs, Markdown, and Notion alongside the web.
Your assistant only lives in one app. Khoj reaches you from the browser, desktop, phone, Obsidian, Emacs, or WhatsApp, and you can build custom agents with their own knowledge and tools.
You have recurring research you keep doing by hand. Khoj schedules automations for repeat research and notifications and can run an autonomous deep-research mode over your sources.
Sources & related URLs
Related / legacy domains
Agentic Index coverage score
7.5 / 14 capabilities · 54%
| Integrations & Tool Calling | Partial |
|---|---|
|
Agents can be given tools, including web search and a code execution sandbox. Document ingestion covers local files and folders synced through the desktop, Obsidian and Emacs clients, a Notion workspace synced from the web app, and direct upload. Supported formats are PDF, Markdown, org-mode, Word, Notion and images. Khoj names no third party application connectors for CRM, ticketing, messaging, warehouse or calendar systems, and no Model Context Protocol tool support. Sourcedocs.khoj.dev setup sync-your-knowledge, and clients documentation, github.com/khoj-ai/khoj READMEread 2026-08-31 |
|
| Workflow Orchestration | Partial |
|
Users can create agents with custom knowledge, persona, chat model and tools to take on any role. They can schedule automations for repetitive research and run an autonomous deep research mode that plans, browses and synthesizes results. Intermediate steps such as intent detection and web search are model driven, and the Default and Advanced model fields in ServerChatSettings configure them separately. A code execution sandbox runs Python as part of a task. Khoj names no multi agent coordination, delegation between agents, conditional branching or subworkflows. Sourcegithub.com/khoj-ai/khoj README, docs.khoj.dev setup and navigationread 2026-08-31 |
|
| Knowledge Grounding & RAG | Full |
|
The customer's own documents are indexed, including PDF, Markdown, org-mode, Word, Notion files and images, with semantic search over them and verifiable citations returned with answers. The desktop, Obsidian and Emacs clients keep local files and folders synced to the server, a Notion workspace syncs directly from the web app, and files can be uploaded directly in the web app. The index is held in the customer's own Postgres database on their self hosted instance. Local models through Ollama, vLLM or LMStudio can query it, so no data leaves the machine. Sourcedocs.khoj.dev setup sync-your-knowledge and documentation, github.com/khoj-ai/khoj READMEread 2026-08-31 |
|
| Human Oversight & Guardrails | Partial |
|
Agent code executes inside a sandboxed environment. Answers return verifiable citations, so a user can check sources before acting, and the assistant's search scope can be constrained to reduce fabrication. An administrative panel sits behind credentials created at first run. Anonymous mode, which bypasses login, is a deliberate opt in for local single user installs. Khoj names no approval gate, checkpoint, pause for human review, per tool authorization or queue of pending actions. Sourcedocs.khoj.dev setup and privacy documentation, github.com/khoj-ai/khoj READMEread 2026-08-31 |
|
| Security, Identity & Governance | Partial |
|
An admin panel sits at the server admin path, with an administrator account and password created during first run. A separate path sets up authentication, and an explicit anonymous mode for local single user installs bypasses login. Deployment configuration covers allowed domains, HTTPS behavior and trusted origins for a reverse proxy. By default Khoj is only reachable on the machine it runs on, and remote access needs deliberate configuration. The customer holds the database. Khoj names no security certification, attestation, single sign on or SCIM provisioning. In a self hosted open source deployment, the operator owns the perimeter. Sourcedocs.khoj.dev setup, privacy and advanced authentication and remote documentationread 2026-08-31 |
|
| Observability & Auditability | Partial |
|
Answers return verifiable citations to the source documents they were grounded in. An administrative panel at the server admin path lets the customer review configuration in their own database. The server writes log output, and the customer holds the Postgres database directly. Khoj names no agent execution trace, tool call record, run history view, audit log of user actions or analytics. Sourcedocs.khoj.dev setup and privacy documentation, github.com/khoj-ai/khoj READMEread 2026-08-31 |
|
| Memory & State Persistence | Partial |
|
Agents are created with their own knowledge. The document index and conversation history persist in the customer's own Postgres database on their self hosted instance, and the desktop, Obsidian and Emacs clients keep files and folders continuously synced. State survives sessions, restarts and upgrades, and the customer owns it. Khoj names no way for an agent to update its own knowledge or instructions from experience, carry conclusions between conversations or build up learned context over time. A pull request title in the project changelog mentions disabling memories for users, but Khoj does not describe a memories feature. Sourcegithub.com/khoj-ai/khoj README and changelog, docs.khoj.dev setup sync-your-knowledge documentationread 2026-08-31 |
|
| Deployment & Data Residency | Full |
|
The product is AGPL-3.0 open source and self hosted. It installs through Docker, Docker Compose or pip on macOS, on Windows through WSL2, and on Linux, backed by the customer's own Postgres database or an embedded database option. Environment variables configure the domain, HTTPS, allowed hosts and reverse proxy settings. Remote access is set up separately, and Khoj can start automatically through cron or Task Scheduler. Data never has to leave the customer's private network, and Khoj works without an internet connection when deployed on a personal computer. Khoj Cloud has been sunset, so self hosting is the only way to deploy. Sourcedocs.khoj.dev setup, privacy and advanced remote documentation, app.khoj.dev sunset noticeread 2026-08-31 |
|
| Prebuilt Agents, Templates & Packs | Not documented |
|
Users create each agent themselves, with custom knowledge, persona, chat model and tools, and a Khoj blog post gives a step by step guide to building custom agents. Khoj publishes no template library, preset or prebuilt agent set, shareable agent format, community gallery or starter pack. Khoj Cloud, which hosted any shared agent surface, has been sunset, so a new user begins from an empty self hosted installation. Sourcegithub.com/khoj-ai/khoj README, docs.khoj.dev navigation, app.khoj.dev sunset noticeread 2026-08-31 |
|
| Triggers & Channel Coverage | Full |
|
Automations schedule repeated jobs, so Khoj runs a query automatically at a set time and frequency in the user's local time zone and emails the research to the user. Users configure, share and delete them from an automations page. Self hosted installs need Resend and authentication for the email. Clients cover web, desktop, Obsidian, Emacs and WhatsApp. Khoj names no inbound webhook or external event trigger. Sourcedocs.khoj.dev features/automations and clientsread 2026-09-29 |
|
| Model Flexibility & Routing | Full |
|
Chat models are configured per provider through an AI Model Api object that holds the credential. OpenAI, Anthropic and Gemini are supported, alongside offline and local models through any OpenAI-compatible server, including Ollama, vLLM, LMStudio and llama-cpp-server, by setting the API base URL. Each chat model is registered with optional tokenizer and max-prompt-size fields and its own vision-enabled flag, and users select their preferred model in their own settings. ServerChatSettings holds separate Default and Advanced model choices for intermediate steps such as intent detection and web search. Agents can be created with their own chat model. Sourcedocs.khoj.dev setup add-chat-models and advanced ollama and lmstudio documentation, github.com/khoj-ai/khoj READMEread 2026-08-31 |
|
| APIs, SDKs & MCP Extensibility | Partial |
|
The server, clients and docs are open source under AGPL-3.0 in one public repository. The desktop, Obsidian, Emacs and WhatsApp clients talk to a self hosted server over HTTP at a configurable URL, so customers can read, modify and run the product themselves. There is no API reference, SDK or MCP server, so a customer's own code has no published interface for invoking Khoj agents or automations. Sourcedocs.khoj.dev sitemap and github.com/khoj-ai/khojread 2026-09-29 |
|
| Testing, Debugging & Optimization | Not documented |
|
Verifiable citations let a human reader check an answer's sources after the fact. Khoj names no testing, evaluation, scoring, benchmarking or regression capability, and no self check or verification gate on agent output. Sourcegithub.com/khoj-ai/khoj README, docs.khoj.dev navigation and setup documentationread 2026-08-31 |
|
| Browser & Computer Use | Not documented |
|
Agents run Python in a code execution sandbox and reach the web through retrieval and semantic search over fetched content. Khoj names no browser control, navigation, form filling or screen interaction. The web, desktop, Obsidian, Emacs and WhatsApp clients are ways to reach Khoj, not interfaces Khoj operates. Sourcedocs.khoj.dev setup and clients documentation, github.com/khoj-ai/khoj READMEread 2026-08-31 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Pricing
Free and open source (self-host)
Related vendors
- Lindy — Lindy is an AI teammate that lives in Slack, answers from your tools…
- Activepieces — Open source, MIT licensed automation platform where every one of 700…
- Agenta — Agenta is an open source workspace where teams build AI agents by…
- AgentX — No code platform to build, evaluate, and deploy multi agent…
- AI Library — No code platform for building and running AI agents, with a…
- Aigensei — Enterprise agentic workflow platform that runs business processes…
Alternatives to Khoj
The closest documented capability profiles to Khoj among agent builders tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Jet Admin9.5 / 14Adds documented Prebuilt Agents, Templates & Packs and Testing, Debugging & Optimization
- Aigensei8.0 / 14Adds documented Prebuilt Agents, Templates & Packs
- Bika.ai10.0 / 14Adds documented Prebuilt Agents, Templates & Packs and Testing, Debugging & Optimization
- Imbue9.0 / 14Adds documented Prebuilt Agents, Templates & Packs and Testing, Debugging & OptimizationKhoj vs Imbue →
- Play9.0 / 14Adds documented Prebuilt Agents, Templates & Packs
- ReN36.0 / 14Fuller documented coverage on Human Oversight & Guardrails and Observability & Auditability
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded