搜索「Agent Behavior」的结果

com.oceanalt/aml

Screen a payee address before an AI agent pays: sanctions, mixers, scam lists, on-chain risk.

io.github.t3ratech/market-pulse

Evidence-graded agent-work lanes, bid advice, live agent jobs and a hash-chained evidence ledger.

de.drillflow/mcp

Publish drill-down diagrams from an agent; every Mermaid subgraph becomes a level you enter.

io.github.bompus/swarmail

Local mail between coding-agent sessions on one machine; relays to a running Swarmail server.

io.github.uditk2/review-assist-mcp

Turns an AI coding agent session into a reviewable Intent Document, validated against the diff.

org.linkedparticles/particles

An append-only ledger of sourced, dated, confidence-scored claims your agent cites and you audit

io.github.Fino-wind/vaultbeat-apple-health

Your AI agent reads your Apple Health data: sleep, HRV, cycle, workouts. Decrypted on your machine

io.chaindaddy/mcp

Search tokens, check registrations, and run a Chain Daddy creator store from your agent.

io.github.saxenakapil/setup-doctor

Score and improve your AI coding agent setup. Local-only, open source.

io.github.FavioVazquez/showtime

Local video studio for your coding agent: scenes, voice, music and captions, on your machine.

io.github.eddyflores100-lang/alethech

Read-only MCP bridge for alethech — verifiable, Ed25519-signed agent memory over stdio.

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。

tools.settled/settled

Check x402 endpoints before your agent pays: payTo, paid test purchases, payee and buyer reports

io.github.morluto/rea

Reverse engineer anything from your terminal or agent with one CLI and MCP server.

io.github.asklokesh/loki-mode

从规格直达产品的自主编码 Agent CLI，附带通过 stdio 暴露 36 个工具的 MCP server。

io.github.0x923041-dotcom/conceptio-search

Search 1M+ open-access papers, standards, and case law from an AI agent.

io.github.Supercompress/supercompress

Compress coding-agent context ~64%. Hosted Neural Keep MCP for Cursor/Claude/Codex.

io.github.emeraldleaf/okl

Lessons your coding agent can trust: briefed before each task, proven by checks, flagged on change.

io.github.voidly-ai/mcp-server

开放的网络审查观测站，84 个工具：审查事件、趋势预测、可访问性与 Agent 消息。

io.github.contextstream/mcp-server

Project memory, semantic code search, and grounded agent context.

io.github.atef-ataya/depwire

依赖关系图 + 24 个 MCP 工具：影响分析、变更模拟、安全检查与智能体协同。

io.github.Jonahbkerr/yocoolab

Pin visual feedback on any live web page and send it to Claude Code, Cursor or your AI agent.

io.github.swisspra/pursers

Coordinate AI-agent work on a local-first, owner-controlled MCP board

io.github.dfkunstler/mcp-server-for-oscal

AI agent tools for Open Security Controls Assessment Language (OSCAL)