This release adds 5 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+2 more
Summary
AI summaryAdds agents, chat streaming, multi‑agent meetings, delegation, custom engine support, and sandboxed execution.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Low |
Adds agents and live chat with streaming reasoning, tool calls, and file edits. Adds agents and live chat with streaming reasoning, tool calls, and file edits. Source: llm_adapter@2026-07-18 Confidence: high |
— |
| Feature | Low |
Adds multi-agent meetings for moderated discussions among agents. Adds multi-agent meetings for moderated discussions among agents. Source: llm_adapter@2026-07-18 Confidence: high |
— |
| Feature | Low |
Adds delegation capability allowing agents to hand work to parallel sessions. Adds delegation capability allowing agents to hand work to parallel sessions. Source: llm_adapter@2026-07-18 Confidence: high |
— |
| Feature | Low |
Adds bring‑your‑own engine support for Claude, ChatGPT, or local models via API key. Adds bring‑your‑own engine support for Claude, ChatGPT, or local models via API key. Source: llm_adapter@2026-07-18 Confidence: high |
— |
| Feature | Low |
Adds schedules, triggers, persistent memory, document/image handling, voice input, interactive artifacts, and community catalogs. Adds schedules, triggers, persistent memory, document/image handling, voice input, interactive artifacts, and community catalogs. Source: llm_adapter@2026-07-18 Confidence: high |
— |
| Feature | Low |
Provides self‑hosted installation via Docker Compose, keeping data on user hardware. Provides self‑hosted installation via Docker Compose, keeping data on user hardware. Source: llm_adapter@2026-07-18 Confidence: high |
— |
| Feature | Low |
Enforces sandboxed isolation by default for each agent, granting access per folder or service. Enforces sandboxed isolation by default for each agent, granting access per folder or service. Source: llm_adapter@2026-07-18 Confidence: low |
— |
Full changelog
Initial public release.
OtoDock is a self-hosted platform for running a team of AI agents on
infrastructure you control. It runs the real Claude Code and Codex as its
engine — so your agents inherit everything the CLIs can do — and wraps them in a
live dashboard, a security model built for shared servers, and the plumbing that
turns a coding tool into a team of coworkers.
Added
- Agents and chat. Every step streams live — reasoning, tool calls, file edits as diffs, plans ticking off. Approve sensitive actions inline, or let trusted agents run unattended.
- Multi-agent meetings. Put specialists in one room for a moderated discussion where agents address each other, answer in parallel, and converge.
- Delegation. Agents hand work to parallel agent sessions you can watch, steer, and continue.
- Bring your own engine. Connect the Claude or ChatGPT plan you already pay for, an API key, or a local model.
- Sandboxed by default. Each agent runs locked down and isolated from your network; you grant one folder or one service at a time.
- Schedules and triggers, persistent memory, documents and images (Word/Excel/PowerPoint/PDF with live preview), voice, interactive artifacts and pinned mini-apps, and community catalogs of installable MCP capabilities and agent templates.
- Self-hosted install via Docker Compose — chats, files, memory and credentials stay on hardware you run.
Install: see the Quick start. Docs: https://docs.otodock.io
Weekly OSS security release digest.
The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.
No spam, unsubscribe anytime.
Share this release
About OtoDock
All releases →Related context
Related tools
Beta — feedback welcome: [email protected]