Changelog

User-facing changes, new features, and notable fixes. For full commit history, see GitHub.

2026-05-23 — Beta 67

New features

Plugin development guide and directory — A new Building Plugins guide covers the full lifecycle for writing, testing, and publishing community plugins. The Plugin Directory page lists official plugins with a process for submitting community plugins.

robota init — project initialization — Running robota init in any directory creates a starter AGENTS.md and .robota/settings.json. If a .claude/ directory is detected, it offers to migrate Claude Code settings automatically.

Local LLM support guide — A dedicated Local LLM Setup guide covers Ollama, LM Studio, and llama.cpp with per-model recommendations. No API key needed for any local inference server.

Context warning banner — The TUI now shows a yellow warning at 70% context usage and a red alert at 90%, with a prompt to run /compact.

Improved /compact output — Running /compact now reports how many messages were removed, the percentage reduction, and before/after context window usage.

3-level permission memory — The permission prompt now has a third option: "Allow always (this project)." Choosing it writes the tool pattern to .robota/settings.local.json so the permission persists across sessions in that project.

2026-05-10 — Beta 60–66

New features

Visual Agent Builder Playground — play.robota.io/playground is a drag-and-drop canvas for assembling agents visually. Drag tools onto an agent node, connect providers, and watch the execution DAG build in real time. Export the canvas as working TypeScript code.

BYOK playground — The playground accepts your own API keys directly in the browser. Keys are passed in-request and never stored server-side.

maxSameToolInputs safety limit — Set maxSameToolInputs on a Robota agent to automatically abort a run if the same tool is called with identical inputs more than N times. Prevents infinite retry loops.

Fixes

Parallel DAG convergence — Fixed a bug that created duplicate edges when multiple parallel agents converged at the same node.

clearChat full reset — /clear now fully resets the session log, DAG state, and conversation history. Previously some DAG events persisted across resets.

Session log correlation — Tool calls in session logs now carry consistent correlation keys, making replay-grade reconstruction reliable.

2026-05-02 — Beta 59

See the full release notes for Beta 59 for a detailed breakdown of all changes in this release window, including:

• Subagent background jobs with transcripts, watchdogs, and command surfaces
• Provider composition: Qwen, Gemma, Gemini, Anthropic, OpenAI, and OpenAI-compatible in one config
• Session log events for replay-grade provenance
• Deterministic parallel Agent tool calls via jobs
• CI/deploy build reuse — single monorepo root build, no per-package rebuild loops

Version history

Stay updated

• Watch GitHub releases for tagged versions
• Subscribe to npm for package updates