One agentic loop. Five context layers. Multi-LLM. Self-host or hosted.
Cotask runs in two configurations. The hosted version is multi-tenant, audited, and production-hardened. The open-source version on GitHub is single-tenant by design and runs on your own infrastructure.
The OSS harness is the same agent loop, the same tools, the same skill format you see described below. The hosted product adds multi-tenant deployment, per-user audit, billing infrastructure, and a production-tuned skill catalog.
The agent loop calls a provider-neutral interface. Switch models per workspace, per skill, or per request.
| Provider | Routing | Notes |
|---|---|---|
| Kimi, GLM, DeepSeek, Qwen | OpenRouter | Pin specific provider + quantization for routing control |
| Anthropic Claude | Direct API or OpenRouter | Compatible with Anthropic's published skills |
| OpenAI GPT | Direct API or OpenRouter | Tool-calling supported |
| Google Gemini | Direct API or OpenRouter | Long-context redlining |
| Llama (open-weights) | OpenRouter or self-hosted | Deployable on your own infrastructure |
| Local (Ollama) | OpenAI-compatible API | Air-gapped deployment supported |
Unlike simple chatbots that respond in one shot, Cotask runs an agentic loop. The LLM receives your message along with a set of tools and autonomously decides which tools to call, in what order, and how many times. It keeps working until the task is complete.
The agent might read a document, search the web, build a spreadsheet, and draft a slide deck, all from a single user message. You see each step as numbered progress items in the chat.
The system prompt is assembled from five layers, each adding more context. You control layers 1–3. The platform handles the rest.
| Layer | Name | Source | Who Controls It |
|---|---|---|---|
| L0 | Platform Prompt | system_prompt.md | Cotask (hardcoded) |
| L1 | agents.md | Your agents.md file | You |
| L2 | Skill Instructions | SKILL.md body | You (customizable) |
| L3 | Playbook | playbook.md | You |
| L4 | Session Context | Documents, active file, conversation | Automatic |
The agents.mdfile is your personal configuration for the AI agent. It sits at the top of the workspace file tree and is injected into every conversation as Layer 1 context. Think of it as “who the agent is” for your workspace.
Edit this file anytime from the workspace sidebar. Changes take effect on the next message. The agent will follow your preferences, match your house style, and focus on the things you care about.
When you type a message, the system assembles the prompt from all applicable layers:
Why this matters: Every layer is a file you can read, edit, and version-control. No hidden prompts, no opaque configuration databases, no vendor lock-in. If you switch platforms, your agents.md, SKILL.md files, and playbook.md come with you.
The playbook (playbook.md) is where you define your team's or organization's standard conventions for common deliverables. The agent loads it as Layer 3 context when drafting, building, or editing.
This is a plain markdown file. Define it once, and every draft, spreadsheet, and deck will follow your conventions consistently. Share it across your team by copying a file.
The tools the agent uses (document reading and editing, spreadsheets, presentations, image generation, web search) are all open source on GitHub. You can audit exactly how your files are processed.
| Category | Tools |
|---|---|
| Document Management | list_documents, read_document, create_document, edit_document |
| Spreadsheets & Decks | create_spreadsheet, edit_spreadsheet, create_presentation, edit_presentation |
| Images | generate_image, edit_image |
| Web Research | web_search, web_fetch |
| DOCX Track Changes | accept_revisions, reject_revisions, get_revision_stats, export_docx |
Skills define which tools the agent can access. The /draft skill gets document tools; the /research skill gets web tools. This keeps the agent focused and efficient.
Start a free trial and explore the workspace file tree. Edit agents.md, customize your playbook, activate skills.