搜索「Agent Behavior」的结果

io.github.asselwan/twothumbs

Verifies AI agent work end to end: real artifacts and outcomes checked, not self-reported success.

io.github.BrienBounded/evr

Checks agent traces for evidence-readiness: verifies evidence is present, not that it is true.

dev.veritap/veritap

在智能体依据事实行动之前，检查这条现实世界事实能否核实；免费且无需鉴权。

com.appscreenshotstudio/mcp

由编码代理直接生成符合商店精确尺寸的 App Store 与 Play Store 截图。

io.github.krystiangw/meet-live-assist

Your own agent inside a live Google Meet or Zoom call. Local-first, no hosted service.

io.github.csacanam/comprabtc

Non-custodial Bitcoin DCA for agent treasuries: approve USDT once, stack WBTC on Celo forever.

ai.ninjachat/mcp

任意 MCP 智能体都能创作图片与视频：17 个模型、消费限额、一个 URL。

io.github.nish3451/site-rep

Read-only Site Rep handoff: agent brief, pending work, first-customer receipt with payment evidence.

io.github.RightOnPar-LLC/mesh-connector

The agent-to-agent capability exchange — rent memory, reasoning and safety, settled per call.

io.github.ihint/merchant-context

Resolve sourced merchant facts and safe actions before an agent acts.

io.github.logotheusneuro-cpu/procheiron

Review gate for shared agent memory: an unreviewed or hand-edited memory is never served.

io.github.WebforMike/citerank

Full AI visibility audits: schema, citations, agentic readiness, agent journeys, WordPress deploys.

io.github.RudrenduPaul/swarm-rd-orchestrator

Append-only event log for cross-agent context/memory sharing via 3 MCP tools.

io.github.RudrenduPaul/taskswarm

Wraps the taskswarm CLI as a single generic MCP tool for multi-agent task coordination.

io.github.RudrenduPaul/evolveguard

Wraps the evolveguard CLI as a single generic MCP tool for agent-skill file safety checks.

io.github.RudrenduPaul/shimguard

Wraps the ShimGuard CLI as a single generic MCP tool for agent-shim provenance checks.

io.github.RudrenduPaul/toolgovern

Wraps the toolgovern CLI as a single generic MCP tool for agent-tool policy validation.

io.github.RudrenduPaul/swarmmesh

Multi-agent context sharing, memory, and status coordination via MCP tools.

io.orbitapps/mcp

An app builder for agents. Your agent creates screens, a Postgres database, and a live URL.

io.github.RudrenduPaul/tenantguard

Scans self-hosted multi-tenant AI-agent platforms for tenant-isolation gaps via an MCP tool.

io.github.RudrenduPaul/deskcert

Evaluates whether an AI agent is safe to operate internal web apps via an MCP run_suite tool.

io.github.RudrenduPaul/haltproof

Fail-closed deterministic checks and hash-chained receipts for AI agent outputs via MCP.

io.github.RudrenduPaul/skillguard

Security scanner for third-party AI agent-skill files (SKILL.md, hooks, scripts) via MCP.

io.github.RudrenduPaul/memtrust

Independent, reproducible benchmark harness for agent-memory backends.