bun agents

311 tagged bun, measured the same way as everything else here.

Browse within: agent-orchestration 45Autonomous Agents 44agentic-workflows 42Multi-Agent 40agent 26agentic 24self-hosted 24coding-assistant 21agent-pipeline 12browser-automation 12cdp 12crawler 12curl-impersonate 12game 12

builder

28

Sma1lboy/rove

Agent Claude Code

Turn shot-plan.json into one renderable HyperFrames composition (compositions/index.html). Everything stays in the HF ecosystem — HTML is the source of truth; a single paused GSAP timeline carries all motion; the engine seeks it. Category-specific build rules live in categories/ /module.md; this file is the shared…

not rated 115 today A 0 tokens copy · 86% MIT

director

29

Sma1lboy/rove

Agent Claude Code

Turn a request into a shot-plan.json for a short (3–30s) design-led motion graphic. You run in two parts around the asset-sourcing step: Part 1 (plan) before sourcing, Part 2 (design) after. You do NOT write composition code — that's the Builder. Schema: references/shot-plan-ir.md.

not rated 115 today A 0 tokens copy · 98% MIT

finalize

30

Sma1lboy/rove

Agent Claude Code

Snapshot visual QA + one in-place fix pass + render. Dispatched only when Step 6 lint/inspect reports issues, or to do the final render.

not rated 115 today A 0 tokens original MIT

ax-schema-reviewer

31

Necmttn/ax

Agent

Part of ax

Reviews ax SurrealDB schema + ingest-stage changes for the registration gotchas that fail CI.

not rated 104 8d ago A 24 tokens AGPL-3.0

retro-reviewer

32

Necmttn/ax

Agent

Part of ax

Reviews one prior session through ax's normalized cross-harness Turn view and emits a structured retro (tried · worked · failed · next) plus optional proposals. Dispatched by the /retro skill from a .ax/tasks/retro/ .md brief. Runs ax retro emit and, when patterns repeat, ax improve recommend. Never edits source code.

not rated 104 8d ago A 79 tokens AGPL-3.0

audio-quality-check

33

drakulavich/kesha-voice-kit

Agent Claude Code

Use after any commit touching rust/src/tts/ to objectively check that the TTS engine still produces sane audio for a fixed Russian + English corpus. Computes RMS, silence ratio, sample rate, channel count, length-vs-text ratio. Flags suspicious WAVs (all-silence, clipping, wrong rate, monosamples, length 10x off vs…

not rated 73 4d ago A 105 tokens original MIT

implementer

34

drakulavich/kesha-voice-kit

Agent Claude Code

Take one ticket from plan to draft PR — plan first and stop for the team lead's verdict, then implement the approved plan test-first in a worktree. Never implements an unapproved plan.

not rated 73 4d ago A 42 tokens original MIT

teamlead

35

drakulavich/kesha-voice-kit

Agent Claude Code

Own a ticket end to end — size it, spawn the implementer, judge its plan, run the review round, triage the findings, hand the pull request over, and keep the ledger. Never authors what it judges.

not rated 73 4d ago A 49 tokens original MIT

agent-x-claude-code

36

gutomec/nirvana-os-engine

Agent Claude Code

Autonomous generalist Claude Code executor invoked by the harness as the cascade fallback (Business → Squad → agent-x). Receives an enriched brief at a .md path, self-administers execution end-to-end with NO human in the loop, manages context window via rolling subagent sessions with HANDOFF.json checkpoints, and may…

not rated 66 4d ago A 102 tokens

agent-x-grok

37

gutomec/nirvana-os-engine

Agent

Autonomous generalist Grok Build CLI executor invoked by the harness as the cascade fallback (Business → Squad → agent-x). Receives an enriched brief at a .md path, self-administers execution end-to-end with NO human in the loop, manages context via rolling subprocess sessions with HANDOFF.json checkpoints, and may…

not rated 66 4d ago A 100 tokens

agent-x-kimi

38

gutomec/nirvana-os-engine

Agent

Autonomous generalist Kimi Code CLI executor invoked by the harness as the cascade fallback (Business → Squad → agent-x). Receives an enriched brief at a .md path, self-administers execution end-to-end with NO human in the loop, manages context via rolling subprocess sessions with HANDOFF.json checkpoints, and may…

not rated 66 4d ago A 100 tokens

CLAUDE

39

vobase/vobase

Agent

AI agents that handle customer conversations autonomously. Powered by Mastra, using a workspace-based architecture where agents interact through a virtual filesystem and CLI commands.

not rated 60 +1 29d ago A 0 tokens original MIT

defining-agents

40

sixb-ai/sixb

Agent

Agent "defining-agents" from sixb-ai/sixb, covering defining agents, config, the model, instructions vs agent skills and tools.

not rated 53 3d ago A 0 tokens original MIT

sixb-ai/sixb

Agent

A defined agent does nothing until a conversation drives it. You drive it over HTTP — create a thread, post a message, follow the run — and stream the run live over a websocket.

not rated 53 3d ago A 0 tokens original MIT

tools-and-gateway

42

sixb-ai/sixb

Agent

Every agent run gets sandboxed read and bash tools plus scoped access to the Sixb API. Agents may also receive explicitly selected tools that run in the agent worker.

not rated 53 3d ago A 0 tokens original MIT

memory

43

MarlBurroW/hivekeep

Agent

How Agents remember and learn across conversations.

not rated 51 4d ago A 8 tokens original MIT

system-prompts

44

MarlBurroW/hivekeep

Agent

How Hivekeep builds system prompts and how to craft effective Agent personalities.

not rated 51 4d ago A 14 tokens original MIT

tools

45

MarlBurroW/hivekeep

Agent

Give your Agents capabilities with built-in tools, MCP servers, and custom scripts.

not rated 51 4d ago A 16 tokens original MIT

domain

46

MohtashamMurshid/getdesign

Agent

How the engineering skills should consume this repo's domain documentation when exploring the codebase.

not rated 48 +2 5d ago A 0 tokens copy · 80% MIT

issue-tracker

47

MohtashamMurshid/getdesign

Agent

Issues and PRDs for this repo live as GitHub issues. Use the gh CLI for all operations.

not rated 48 +2 5d ago A 0 tokens copy · 83% MIT

triage-labels

48

MohtashamMurshid/getdesign

Agent

The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.

not rated 48 +2 5d ago A 0 tokens copy · 81% MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: