blast-scope 命令影响评估
v0.6.1
io.github.Atharva-Jayappa/blast-scope
为 AI 代理即将执行的 shell 命令给出结合上下文的爆炸半径(影响范围)评分。
“Multi Agent” 共 2,739 个结果
v0.6.1
io.github.Atharva-Jayappa/blast-scope
为 AI 代理即将执行的 shell 命令给出结合上下文的爆炸半径(影响范围)评分。
v1.0.2
io.github.farshadmomo/lan-direct
Browser MCP: the app under test egresses via the real ISP while the agent stays on the VPN.
v2.2.17
io.github.AkashGoenka/coldstart
Codebase memory for AI agents: an AST index plus agent-written notes that self-stale.
v0.7.2
io.github.RamaAditya49/titen-memory
Evidence-grounded agent memory with mandatory provenance, on local SQLite or Cloudflare D1
v0.1.0
io.github.a202-protocol/a202-mcp
Verifiable agreements for agent-led commerce: mandates, obligations, evidence, transaction records.
v0.14.5
io.github.tenequm/pond
Lossless archive and search for AI agent sessions across clients, exposed to agents over MCP.
v0.3.1
io.github.richardofortune/tyrekick
直接在编程智能体里读取并处理钉在在线原型上的人类反馈。
v0.1.4
io.github.CoralLips/gft-mcp
Bring your GFT (Git for Thought) white-box thinking map to any AI agent. 把你的思维脉络接给任何 agent。
v1.0.7
io.github.AkaciaNL/basicdeploy-mcp
The runtime your agent deploys to — DB, storage, and a public URL in one MCP call.
v1.0.38
io.github.Gorgon-Cyber/gorgon-scout
从 Claude 或任意 MCP 智能体发起 AI 驱动的 Web 应用与 API 安全扫描(DAST),仅支持 Windows。
v0.4.34
io.github.cerebrixos-org/tuning-engines
以策略、审批、追踪与用量分析治理模型、智能体、技能和 MCP 工作流。
v0.1.23
io.github.udah1/cursor-chat-bridge
Drive the Cursor agent from Telegram, Discord, or GitHub — with images and voice notes.
v0.3.0
io.github.Wuesteon/lean-memory
Embedded, local-first agent memory: one SQLite file per namespace, no server, no cloud.
v0.13.0
io.github.tiagosilva07/zyrax-guard
审计 AI 智能体配置中的提示注入与可疑 MCP 服务器,并对第三方依赖包进行甄别。
v0.1.2
io.github.tomcat65/engram
Coordination bus + shared truth for AI agent fleets — self-hosted MCP server + stdio bridge.
v0.11.0
io.github.aibenyclaude-coder/kira
面向 AI 智能体的技能与伤痕:你的智能体记录自己的失败,并且不再重犯。
v0.3.0
io.github.mindstone/mcp-server-retell-ai
Retell AI MCP 服务器:语音智能体电话呼叫、智能体管理、模型与音色查询。
v0.7.1
io.github.LufeMC/kaval
在代理行动前核验其行动所依赖的事实——返回 ALLOW、REVIEW 或 BLOCK。
v0.1.1
io.github.dwarehouse1/vrm-toolkit-mcp
Inspect, validate and preview VRM / VRMA files from an AI agent (5 tools, local stdio server).
v0.1.20
io.github.ndesv21/socialclaw
将任意 AI 代理接入 11+ 个社交平台:经托管 MCP 排期、发布并追踪帖子。
v0.1.1
io.github.kakha13/esim-mcp
Compare travel eSIM plans by country, and regional vs local pricing for multi-country trips.
v0.2.1
io.github.soteeabam/looppause
LoopPause MCP server — pause agent execution and route human approval requests
v0.2.3
io.github.sekharsdet/five46
BYOK, fully local AI agent that tests your app/API and writes a real Playwright spec on success.
v1.2.0
io.github.elberacasa/umbra
Trust score for AI-generated code: scan repos, guard agent file writes, get a 0-100 score.