trust-scoring 开源项目推荐（52 个）

2ndSetAI /good-egg

Trust scoring for GitHub PR authors based on contribution history.

NexoCoop /nexo

NEXO runtime core for NEXO Desktop: local memory, automation, MCP tools and update-managed runtime.

rayyagari2-create /agentic-workforce-framework

An operating model for autonomous agent teams. Identity, task contracts, failure memory, trust scoring and audit for teams that want to operate agents as an accountable workforce.

Basaltlabs-app /Gauntlet

Community-driven behavioral reliability benchmark for LLMs. 231 probes across 19 modules, deterministic scoring, perplexity correlation, layer sensitivity mapping, quant method capture, hardware-stratified community rankings. Every test contributes to the community dataset.

sunilgentyala /SybilShield-Core

A modular composite trust scoring framework for Sybil-resilient permissionless blockchain networks

yablokolabs /truthlens

AI hallucination detector with formally verified trust scoring for LLM outputs. No API keys needed.

mguard-ai /mguard

Memory defense for AI agents — stops MINJA, AgentPoison, and MemoryGraft attacks. Zero dependencies.

getmcpm /cli

MCP security guard + package manager. Block prompt injection, tool poisoning and rug-pulls in Model Context Protocol servers at runtime; trust-scored installs with Sigstore provenance for Claude Desktop, Claude Code, Cursor, VS Code, Windsurf and Gemini CLI. Local, deterministic, no LLM in the loop.

Fachryxyf /scorpio-guard

Adaptive trust evaluation for web interactions - trust as a spectrum, not a verdict. Local advisory library over an open symptom/prescription protocol. Design phase.

Savunma-Sanayi-Teknolojileri-Toplulugu /sensor-trust-lab

Sentetik sensör verileri, ölçüm güveni, tutarlılık ve takip güvenilirliği için TSSTT araştırma laboratuvarı.

Dmitrze /repo-trust

Multi-dimensional GitHub repository trust scoring beyond stars — federates OpenSSF Scorecard, deps.dev, OSV. Apache-2.0.

mahsumaktas /agent-evolution-kit

Multi-agent orchestration with self-evolution, cognitive memory, and governance.

broomva /life

Open-source Rust runtime for autonomous agents — 13 modules, 76 crates, 2625 tests. Event-sourced persistence (Lago), homeostatic regulation (Autonomic), x402 payments (Haima), cryptographic identity (Anima), distributed networking (Spaces), metacognitive evaluation (Nous), OpenTelemetry observability (Vigil).

enchanter-ai /crow

Bayesian change-trust layer. Autonomously scores every AI code edit in real-time, instantly flagging the exact files that demand human review.

Garl-Protocol /garl

该项目在 GitHub 上没有填写描述

veriswarm /veriswarm-sdk

Official SDKs and MCP server for VeriSwarm — trust infrastructure for AI agents

stchakwdev /Ansib-eL

AI-native version control system that extends Git for autonomous agent workflows. Tracks decisions, not just diffs. Tournament-style parallel execution, trust-based reputation scoring, and full chain-of-thought lineage.

mrkingsleyobi /trustswarm

Real-time blockchain fraud detection using autonomous multi-agent AI swarms. Detect fraud in <2s with 150x faster vector search (HNSW), 84.8% accuracy, and 73% cost reduction. Features ERC-1155 trust scores, MCP integration, and reflexion learning.

ArtLjn /mnemo

Structured fact memory MCP server — SQLite + FTS5, trust scoring, entity graph, auto-observe, bilingual retrieval for AI coding assistants

BeBraveBeKind /mcpskills-server

Official MCP server for mcpskills.io — pre-install trust scores, safety scans, auto-gate. @mcpskillsio/server (io.mcpskills/server). Not affiliated with mcpskills.dev.