lthoangg/OpenAgentd

Score8.0

Popularity197.0

Risknone

TierGold

Score breakdown

Usefulness9.0

Novelty8.0

Momentum8.0

Maturity8.8

Open-source/build8.4

Evidence8.0

Workflow potential9.5

Setup ease8.8

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for AI-power-users who want a desktop cockpit for running teams of AI agents — OpenAgentd is the double-click-install desktop app with a real UI to watch every step (vs terminal-only Claude Code / Codex CLI), command palette (Ctrl+P), slash commands (`/init`, `/continue`, `/compact`, `/undo`, `/redo`), and a tool inspector that shows every tool call with inline Git-like diffs; for engineeri

Who should use it

AI-power-users who want a desktop cockpit for running teams of AI agents — OpenAgentd is the double-click-install desktop app with a real UI to watch every step (vs terminal-only Claude Code / Codex CLI), command palette (Ctrl+P), slash commands (`/init`, `/continue`, `/compact`, `/undo`, `/redo`), and a tool inspector that shows every tool call with inline Git-like diffsEngineering teams that want a multi-agent system with lead + workers visible in a split-pane live view — OpenAgentd's lead agent spawns specialist instances on demand, coordinates through an async mailbox, and can grant/revoke member tools/skills/MCP servers at runtimeDevelopers that want persistent memory across sessions — OpenAgentd uses the Karpathy wiki pattern with `USER.md` injected into every prompt, session notes feeding the dream agent, and durable knowledge organized into sources/topics/entities/comparisonsUsers that want provider flexibility (15 providers: Anthropic, Gemini, OpenAI, OpenRouter, Bedrock, Grok, DeepSeek, Ollama, and more) — switch with one line in the agent config or override the lead model / thinking level per session from Session SettingsEngineering teams that want local-first operations — voice input via browser/OS speech recognizer (no backend audio transcription), scheduled tasks on cron/interval/one-shot timers, live todo board, telemetry dashboard that stays local with no third-party SaaSEngineering teams that need git-worktree-isolated coding sessions — create worktrees from the repository tree, rename sidebar titles, remove OpenAgentd-managed worktrees from the UI when doneUsers that want cross-chat `/undo` — restores workspace files from any prior turn (not available in Claude Code / Codex CLI)Engineering teams that need a desktop app alternative to Cursor / Windsurf — OpenAgentd is Apache-2.0 with your keys vs Cursor / Windsurf's $20/mo+ subscriptionUsers that want a desktop multi-agent team experience comparable to Claude Code or Codex but with a real UI — OpenAgentd's `coding/openagentd`, `coding/coder`, `coding/explorer` team is the documented coding surface

Who should skip it

Consider lthoangg/OpenAgentd lower priority if you already have a working solution in this category.

About this signal

lthoangg/OpenAgentd is tracked by RepoRadar as a desktop agent cockpit with multi in the Apache-2.0 desktop agent cockpit (double-click i section. It was first seen on 2026-06-25 and last updated on 2026-06-25. The current verdict is 'try now' with a Gold tier and easy setup difficulty. Across RepoRadar's eight signals, lthoangg/OpenAgentd is strongest on workflow potential (9.5) and practical usefulness (9.0) and weakest on evidence quality (8.0) — a profile worth weighing against your own priorities. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.

How this item is evaluated

RepoRadar assigned lthoangg/OpenAgentd a composite score of 8.0 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 197.0 and never affects the composite score or tier. The risk label of 'none' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.

Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.

Risk explanation

No inherent user-impacting risk is flagged from the captured evidence.

Evidence links

github.com

Closest alternatives / related signals

openagentdlthoanggdesktop-agentagent-cockpitmulti-agentlead-agentspecialist-workersasync-mailbox