搜索「Agent Behavior」的结果

io.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/revoke

signed revocation lists for agent cards, keys, and mandates — one feed, every registry, revocation

io.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/meter

Cross-provider agent spend analytics — one ledger for tokens, tools, and payments.

io.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/marquee

The live-events agent: it finds the event, watches the price, buys only inside your mandate, and

io.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/mail

Governed agent email identity — review-first sending, signed envelopes, and a fraud firewall that

io.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/keyhold

credential leases, never raw keys — scoped, expiring secret leases for agents; the agent gets a

io.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/health-check

Scan an MCP server or agent configuration for security posture — evidence-bound findings

io.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/envoy

The signed front door for agent-to-agent business: vetted in, tier-told, drafted — never bound

io.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/environment

The smart-environment module — scopes an agent's authority to actuate a home, tier by tier, and

io.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/countermark

One verification call for third-party agent cards and payment mandates — a receipted verdict a

io.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/consent

per-agent, per-purpose consent receipts for personal data — a grant an agent must present, and a

io.github.CYAN-ECLIPSE-TECHNOLOGIES-LLC/blackbox

The record that survives the agent: append-only, recorder-signed, and graded by proof — never by

io.github.manhliemcn4euwlu-source/llm-red-team-scanner

LLM agent security review: live injection/jailbreak probes plus a static audit of missing guardrails

app.brightlyai/brightly

Run your Brightly account from your AI agent: leads, conversations, appointments, sequences.

al.ephemer/ephemeral

Run AI agent tasks in isolated sandboxes with a cost cap, saved workflows and scoped connections.

io.github.xixi048/publish-to-all-skill-stores

List, check and package a SKILL.md skill for every agent-skill store.

com.scopeblind/protect-mcp

为智能体工具调用提供 fail-closed 的 Cedar 策略闸门与 Ed25519 签名回执，任何出错即拒绝。

io.github.iris-eval/mcp-server

别再凭感觉上线智能体——为每一次智能体输出评估质量、安全性与成本。

io.github.bytesbrains/16ane

Budget-capped agent wallet: pay x402 services in tANE, a free testnet token with no cash value

io.github.SadaSend/sadasend

Transactional email API & AI agent safety runtime with 12 scoped tools and SpendGuard.

net.bigfloppy.page2md/page2md

Turn any webpage into clean Markdown for LLM/agent pipelines. Free tier; paid 1 USDC = 1000 req.

com.radiance-app/radiance

Translate, dub and publish videos to TikTok, YouTube, Instagram and more from your AI agent.

app.frame24/frame24

Make narrated, on-brand product videos of your real app from your coding agent or AI assistant.

io.github.remembra-ai/remembra

持久化 AI 记忆：实体解析、时序知识图谱，含 11 个 MCP 工具。

dev.signops/signops

Send push to Android, iOS and the web, and ask a trusted phone to approve a login, from your agent.