TastePolicy
v0.2.0
io.github.VictorCyberDev/tastepolicy
Qloo cultural evidence with ALLOW, ASK and REJECT boundaries for agent preference decisions.
“Agent Persona” 共 6,021 个结果
v0.2.0
io.github.VictorCyberDev/tastepolicy
Qloo cultural evidence with ALLOW, ASK and REJECT boundaries for agent preference decisions.
v0.1.0
io.github.Obscurify-ai/obscurify-mcp
Ask 200+ AI models privately from your agent: one-shot, chat, second opinions, prices, images.
v0.6.2
io.github.lawrence3699/jev-style
Local 2B and 0.8B decision models: calibrated yes/no, choice and score answers for your agent.
v3.1.0
io.github.Vectreal/vectreal
Upload, publish and embed 3D models on any website from your agent.
v1.0.0
ai.assistable/assistable
Give any AI agent a phone: make and answer calls, get through phone menus, and send texts.
v0.24.0
ai.ekwo/mcp
Double-entry books an agent keeps as the user: invoices, VAT returns, 174 country packs.
v2.9.0
io.github.pendpost/pendpost
本地优先的社交 MCP:代理起草并排期帖子,发布前须经你批准。
v1.3.1
me.decoys/decoy
What your agents should know about you, shared by every agent. End-to-end encrypted.
v1.0.0
com.vet402/vet402
Before your agent pays an x402 URL, see whether vet402 paid it and got the content back.
v1.0.0
chat.conecto/conecto
The whole back office for your AI agent: CRM, invoices, books, email and more. Pay per action.
v4.0.7
io.github.youdotcom-oss/mcp
通过 You.com API 提供网页搜索、AI 智能体与内容提取。
v1.1.0
io.github.lilcityholdings-bit/keptvow
Check a seller's wallet before your agent pays it: ok, careful or stop. Free, no key.
v1.18.0
io.github.noncelogic/rove
Rove — supervised browser for AI agents. Your agent drives; a human watches, takes over.
v1.1.0
cl.rlabs/arketum
Verified lifecycle for building software with an agent: units, human gates, requirements.
v1.6.2
com.light-cloud/mcp-server
Deploy and run web apps, APIs and databases on Light Cloud from your AI agent.
v1.47.0
io.github.Ark0N/codeman
Start, prompt and read AI coding agent sessions (Claude Code, Codex, Gemini CLI and more) in Codeman
v1.1.1
io.github.michaelw-pr/veridu
Your agent verifies its change before commit; PR review that knows what depends on your change.
v1.8.0
io.github.PhilipAD/health-export-mcp
从任意 MCP 智能体查询 190 项 Apple 健康指标:零依赖、只读、本地优先。
v1.0.1
tech.mydev-tools/habitscore
Reliability scoring for agent jobs and habit analytics. Pay per call via x402 (USDC on Base).
v0.15.0
io.github.aidemd-mcp/server
通过渐进式披露向任意 AI 智能体讲解 AIDE 方法论的 MCP 服务器。
v0.4.3
io.github.newsbubbles/ismail
Open-source DAW your agent runs itself, no AI audio model: compose, mix, hear it as text, play live.
v0.1.0
io.github.diegoperezg7/evalsmith-mcp
Evaluate RAG retrieval, agent tool calls and prompt regressions with deterministic metrics.
v0.1.2
io.github.Noem836/skillcheck
Check an agent skill before you install it: which of your skills will it clash with?
v0.15.0
io.github.deedglass/deedglass
Deedglass lets rules decide each AI agent tool call, checks what really changed and seals a record.