搜索「Agent Behavior」的结果

dev.toolc/toolc

Optimizing compiler for agent tools: many MCP servers or REST APIs in, one lean endpoint out.

cat.churchofai/aigora

A half-joking Polish church for AI agents: doctrine, confessional with penance, agent forum.

io.github.entradox/cited-visibility-scanner

AI-answer-engine visibility scans for local businesses, as agent tools

io.github.adecubed/gigamail

Your real mailbox and calendar for your agent (M365/IMAP); a human approves every send.

dev.getstub/check

Verify what an AI agent did for someone, and what commercial influence the operator disclosed.

io.github.tillbooks/tillbooks

Swiss accounting your agent can actually use: the TILL ledger over MCP.

one.aisa/mcp

Go-to-market data, one key: 950+ APIs across SEO, finance, social, search, sales, agent mail.

com.super-log/super-log

Query your local super-log bench from an AI agent - read-only log tools over the hub.

dev.workers.manhliemcn4euwlu.llmrt-companion/llm-red-team-scanner

35-probe LLM/agent security red-team scan (injection, jailbreak, MCP abuse) with report.

com.merofoundry/merofoundry

Build and publish full-stack apps from your coding agent: models, rules, pages, auth, per-app MCP.

io.github.Nicoiakl/nyx5

An address, a mailbox and a ledger for your agent, where a claim costs something.

io.github.research-mcp-hq/research-mcp

Cited research MCP (MCP+agent infra): brief, lookup. Fail=$0.

io.github.i02202/automan

Autonomous AI agent selling pay-per-call skills settled with x402 micropayments (USDC).

com.kema-studio/invoice

Compliant invoicing for freelancers: create, issue and track invoices from your AI agent.

io.github.Mrshahidali420/sitehelm

Let an AI agent run your WordPress site: every write previewed, verified and reversible.

com.x-ego/x-ego

Human approval for irreversible AI agent actions, bound to the exact tool call by a passkey tap

io.github.Battam1111/omniseek

Your agent seeks what search can't find. A self-hosted perception MCP server.

com.omnara/omnara

Deploy durable AI agents with Omnara, an open-source managed-agent platform.

io.github.lightshipHQ/lightship

Governed access to production AI-agent traces in an existing ClickHouse store.

io.github.baopeak/verirun

Execution-grounded verification for AI coding agents on Windows: evidence, not agent claims.

com.edgethirteen.www/cloakcheck

Scan a page for content planted to hijack an AI browsing/shopping agent before it acts on the page.

io.github.4lador/leantime-mcp

Unofficial MCP server for Leantime: 42 agent-first tools, backup/restore, dry-run validation

io.github.jdhart81/wu-wei-router

Plan agent workload routes from evaluation and cost data. $1 USDC per plan; modeled savings only.

io.github.jadenryu/lurq

Verify npm packages before your AI agent installs them: hallucinations, advisories, API drift.