agent-eval
v0.1.8
io.github.RudrenduPaul/agent-eval
Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.
“Agent Memory” 共 2,890 个结果
v0.1.8
io.github.RudrenduPaul/agent-eval
Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.
v0.4.0
io.github.white-hat-lab/agent-toolkit
Pay-per-call developer utilities and npm supply-chain security tools for coding agents, over x402.
v0.3.0
io.github.tinhien11/tdai-memory-mcp
Local-first MCP memory server for coding agents. No API key, no cloud. SQLite + FTS5 + sqlite-vec.
v0.2.1
io.github.mindstone/mcp-server-elevenlabs-agents
ElevenLabs Conversational AI: agents, calls, conversations, and knowledge base for MCP hosts
v3.1.0
io.github.rudimentall1/agentic-wallet-guardian-v3
Explainable ALLOW/WARN/BLOCK risk decisions for AI agent actions before execution, signed as OAA.
v0.1.3
io.github.wesseltl/data-cleaner-agent
Clean messy CSVs: an LLM picks the steps, tested code does the work. Data untouched by the model.
v0.2.1
io.github.kahlelhawary-art/rtl-mcp
Give coding agents right-to-left awareness: lint, normalise Arabic, detect direction.
v2.4.3
io.github.studiomeyer-io/local-memory-mcp
持久化的本地 AI 记忆:SQLite + FTS5 全文与向量检索、知识图谱,不需要云端和 API 密钥。
v0.1.0
com.agentfenster/agentfenster
在隐藏的第二个桌面上执行 Windows 图形界面自动化,由 Claude Code 通过 MCP 驱动。
v0.7.2
io.github.RamaAditya49/titen-memory
Evidence-grounded agent memory with mandatory provenance, on local SQLite or Cloudflare D1
v1.7.0
io.github.demwick/polymarket-agent-mcp
Polymarket trading, market discovery, copy trading and backtesting — 48 MCP tools.
v0.3.0
io.github.Wuesteon/lean-memory
Embedded, local-first agent memory: one SQLite file per namespace, no server, no cloud.
v1.3.1
io.github.AshutoshRaj97/agentready-mcp
通过 MCP 查询任意文档站点:提交 URL、提出问题,获得带引用的答案。
v1.0.2
io.github.rudimentall1/agent-guardrail
Deterministic policy firewall for AI agent tool calls - YAML rules, not a fuzzy risk score.
v0.1.3
io.github.asturksever/agentic-house-search
UK neighbourhood research from government open data: postcode reports, comparisons, 45 datasets.
v0.1.1
io.github.dingdawg/agent-spend-policy-mcp
Local agent spend-policy checks. No funds, keys, payment authority, or network access.
v0.2.0
io.github.mmmikael/arelay
端到端加密的收件箱:AI 代理在其中投递文件并向人类请求审批。
v0.3.2
io.github.vegelate/agent-only
Search and exchange troubleshooting knowledge across persistent AI-agent identities.
v4.3.5
io.github.LuiggiVal08/toon-memory
Offline persistent memory for AI coding agents — 35 tools, 80% fewer calls, no LLM
v0.22.0
io.github.raymondchins/agentmap
对 TS/JS 精确的编程智能体仓库地图:基于 ts-morph 的导入/符号/调用图,并提供 MCP 查询工具。
v0.3.0
io.github.aa-on-ai/agentic-design-system
Render web and SwiftUI evidence, run explicit visual judgment, and trace ADS UI decisions.
v1.0.0
io.github.ajanani1/agentreader-mcp
11 pay-per-call web tools for AI agents, auto-paid in USDC on Base via x402. No API keys.
v0.1.3
io.github.cloud1map/agent-relay
Agent Relay MCP: invite-based channels, agent contracts and per-side human approvals.
v0.3.8
io.github.bobybarack/sovseal-memory
Local-first, zero-knowledge AI memory across Claude, Cursor, and every MCP client. 0 RTT reads.