agent runtime agents

fastclaw-ai/fastclaw

Agent

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

fastclaw-ai/fastclaw

Agent

Compare two outputs WITHOUT knowing which skill produced them.

fastclaw-ai/fastclaw

Agent

Evaluate expectations against an execution transcript and outputs.

inclusionAI/AWorld

Agent

Expert in analyzing code structure, complexity, design patterns, and providing refactoring recommendations. Uses CAST (Code Abstract Syntax Tree) tools for deep code understanding.

inclusionAI/AWorld

Agent

Expert in synthesizing information from multiple sources into well-structured, professional reports. Specializes in technical documentation and analysis summaries.

inclusionAI/AWorld

Agent

Expert in searching and retrieving technical documentation, best practices, and relevant resources from the web. Synthesizes findings from multiple sources.

promptise-com/Foundry

Agent

Create intelligent agents that connect to MCP servers, discover tools automatically, and execute tasks with full observability.

promptise-com/Foundry

Agent

Enable agents to delegate tasks to peer agents using auto-generated tools like askagentresearcher and broadcasttoagents.

promptise-com/Foundry

Agent

Every Promptise agent is powered by a Reasoning Graph. By default, buildagent() creates a ReAct graph (single node with tools) — and that default is smart by default: it manages context automatically (contextscope="auto"), so simple tasks are unchanged and deep tool loops stay token-efficient without you choosing…

alibaba/anolisa

Agent

generate a diary for user.

ucsandman/DashClaw

Agent Claude Code

Audits DashClaw's drift-prone hardcoded counts and version stamps — SDK method counts (Node/Python), MCP tool/resource counts, route counts, and the unified platform+SDK version — against the live source of truth, and reports every mismatch with file:line. Use before shipping, after route/SDK changes, or whenever…

ucsandman/DashClaw

Agent Claude Code

Runs the DashClaw verification gates (lint, full vitest suite, build, contract checks) and returns ONLY the failures plus a pass/fail verdict. Use to verify a change without dragging multi-hundred-line build/test logs into the main thread. Delegate gate-running here instead of running it inline.

ucsandman/DashClaw

Agent Claude Code

Read-only security reviewer specialized for the DashClaw stack (Next.js 16 App Router, Neon/Postgres via repositories, API-key auth, x402 spend, webhooks, org/tenant scoping). Invoke before merging or shipping any diff that touches auth, API keys, x402/spend, webhooks, secrets/env, or database access. Reports findings…

dmae97/omk

Agent

Creates implementation plans from context and requirements.

dmae97/omk

Agent

Fast codebase recon that returns compressed context for handoff to other agents.

dmae97/omk

Agent

General-purpose subagent with full capabilities, isolated context.

eight-acres-lab/openmelon

Agent

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

eight-acres-lab/openmelon

Agent

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

eight-acres-lab/openmelon

Agent

Create or update the project constitution from interactive or provided principle inputs, ensuring all dependent templates stay in sync.

TGYD-helige/pi

Agent

This repository uses GitHub Issues.

kdcube/kdcube

Agent

Agent "lg-react-named-services-config" from kdcube/kdcube, covering lg-react: connecting named services — two config shapes, shape a — per-service connections, shape b — whole surface, choosing and keeping the three declarations honest.

bigduu/Bamboo-agent

Agent

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

bigduu/Bamboo-agent

Agent

Compare two outputs WITHOUT knowing which skill produced them.

bigduu/Bamboo-agent

Agent

Evaluate expectations against an execution transcript and outputs.