28 packages found
(S)AGE - (Sovereign) Agent Governed Experience
Honest claim corroboration for AI agents (MCP server): syndication-aware independent-source counting, confidence scores,
Zero-dependency agent memory + MCP server. Value-ranked recall, consolidation, and a first-class correction & erasure ch
Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewritin
Graph memory for AI agents — decisions, context, and session history that survive across every conversation. Works with
mcp-funding-press-signal-scanner
Pre-submission AI review stress-test for research papers. A Claude Code skill: review, verdict, revise, verify.
A Multi Agent Memory MCP That Connect Agents Across Systems and Machines
AI memory engine exposed as an MCP server
Agents make claims. Reelier writes receipts — record an agent's tool-call workflow once, replay it deterministically at
Free web search for AI agents — multi-engine parallel, smart re-ranking, zero API keys. | 免费 AI 联网搜索 — 多引擎并行、语义重排、零 API
A deterministic crash diagnosis engine for .ips reports (CLI + MCP server)
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers
Deterministic research MCP server on FastMCP 3 — 5-engine web search, 9-platform social search, 6 academic DBs, news agg
Mythos Router 2026: Zero-Drift Local Reasoning Protocol with Adaptive Claude Opus 4.8
Automated security investigation tool using Microsoft MCP Servers, GitHub Copilot, Python Modules and custom copilot-ins
Turn your markdown vault into a compounding knowledge wiki (Karpathy inspired). Six agent skills - knowledge grows with
Cross-Code Organizer (formerly Claude Code Organizer): cross-harness config dashboard for Claude Code, Codex CLI, MCP se
The first multi-source MCP server for Philippine civic data: earthquakes, weather, typhoons, procurement, population, po
MCP server that channels JVM forensics into structured leak verdicts — for Claude Code.
The Google for AI agents — give Claude the power to research any company, analyze competitors, and track market trends.
Manage AWS, Hetzner, OVH, and custom servers from one TUI — with a built-in AI assistant and MCP server
Hypothesis-driven problem solving for AI agents: probe, falsify, escalate — never blind-retry. MCP server + agent skill
An open framework for scoring how well an MCP tool definition communicates to an AI agent – the Tool Definition Quality
OSINT suite for Claude — 898 curated OSINT tools as an Agent Skill + MCP server (classifier, URL builder, IBAN check, PI
Policy-as-code for MCP agents: deny risky tool calls before they run, prove what ran with verifiable evidence, and enfor
Open-source (Apache-2.0) PDF takeoff for construction & flooring — the first engine an AI agent drives natively over MCP