Trust scoring for GitHub PR authors based on contribution history.
-
Updated
Apr 12, 2026 - Python
#
trust-scoring
Here are 52 public repositories matching this topic...
Local-first memory governance for AI agents: shared, reviewable, auditable memory via SQLite and MCP.
sqlite mcp multi-agent knowledge-base obsidian ai-agents rag local-first llm sqlite-vec mcp-server agent-memory memory-governance trust-scoring
-
Updated
Aug 27, 2026 - Python
NEXO runtime core for NEXO Desktop: local memory, automation, MCP tools and update-managed runtime.
memory mcp knowledge-graph semantic-search codex cognitive-architecture metacognition rag vector-search shared-brain local-first autonomous-agent ai-memory model-context-protocol mcp-server claude-code trust-scoring claude-code-plugin atkinson-shiffrin natural-forgetting
-
Updated
Jul 3, 2026 - Python
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.
enterprise multi-agent self-learning autonomous-agents ai-agents audit-trail operating-model trust-score llm agentic agentic-ai claude-code trust-scoring agent-governance agent-governance-autonomous-systems failure-memory agent-governance-toolkit agent-governed
-
Updated
May 30, 2026 - JavaScript
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.
benchmark mcp community-driven model-evaluation ai-evaluation llm ollama sycophancy hallucination-detection llm-testing hardware-benchmark ai-trust trust-scoring behavioral-testing llm-benchmark deterministic-scoring
-
Updated
May 4, 2026 - Python
Memory defense for AI agents — stops MINJA, AgentPoison, and MemoryGraft attacks. Zero dependencies.
firewall owasp ed25519 ai-agents ai-security langchain eu-ai-act mem0 agent-security minja memory-poisoning trust-scoring
-
Updated
Mar 9, 2026 - TypeScript
Runtime security guard for MCP servers, plus the package manager to install them. Search, install, audit, and guard across Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Gemini CLI.
cli security package-manager ai mcp vscode cursor claude runtime-security prompt-injection model-context-protocol mcp-server trust-scoring
-
Updated
Sep 2, 2026 - TypeScript
Adaptive trust evaluation for web interactions — trust as a spectrum, not a verdict. Local advisory library over an open symptom/prescription protocol. Design phase.
security web-security bayesian anti-bot bot-detection fraud-detection open-core privacy-by-design open-protocol behavioral-analysis anti-scraping trust-scoring
-
Updated
Aug 24, 2026 - HTML
Multi-agent orchestration with self-evolution, cognitive memory, and governance.
orchestration multi-agent memory-management cognitive-science governance ai-agents reflexion agent-framework llm prompt-evolution cognitive-memory self-evolution trust-scoring
-
Updated
Mar 3, 2026 - Shell
Multi-dimensional GitHub repository trust scoring beyond stars — federates OpenSSF Scorecard, deps.dev, OSV. Apache-2.0.
github rust cli opensource dependency-analysis developer-tools osv scorecard deps-dev supply-chain-security fake-stars trust-scoring
-
Updated
Jul 20, 2026 - Rust
Sentetik sensör verileri, ölçüm güveni, tutarlılık ve takip güvenilirliği için TSSTT araştırma laboratuvarı.
-
Updated
Aug 5, 2026
Bayesian change-trust layer. Autonomously scores every AI code edit in real-time, instantly flagging the exact files that demand human review.
-
Updated
Sep 1, 2026 - Shell
A modular composite trust scoring framework for Sybil-resilient permissionless blockchain networks
python peer-to-peer blockchain consensus network-security federated-learning sybil-attack trust-scoring
-
Updated
Jul 26, 2026 - Python
Cryptographic verification for AI agent actions — ECDSA-secp256k1 + RFC 6979 signed Action Receipts (v0.1), multi-dimensional Trust Vector, capability tokens (JWT-shaped + Biscuit-style attenuation), UETA §10(b) undo. 29 MCP tools. A2A v1.0 + ERC-8004 format compatible. Receipt-batch Merkle roots anchored on Base mainnet. Starting with code.
mcp protocol ecdsa trust reputation ai-agents fastapi a2a ueta langchain crewai trust-scoring agent-economy erc-8004 agent-trust capability-tokens action-receipts trust-vector
-
Updated
Aug 3, 2026 - Python
AI hallucination detector with formally verified trust scoring for LLM outputs. No API keys needed.
python rust offline-first mcp wikidata formal-verification fact-checking ai-safety lean4 llm-evaluation hallucination-detection trust-scoring ai-reliability claim-extraction
-
Updated
May 23, 2026 - Rust
Official SDKs and MCP server for VeriSwarm — trust infrastructure for AI agents
nodejs python sdk mcp ai-safety ai-agents ai-governance langchain model-context-protocol mcp-server trust-scoring agent-trust
-
Updated
Aug 24, 2026 - Python
Official MCP server for mcpskills.io — pre-install trust scores, safety scans, auto-gate. @mcpskillsio/server (io.mcpskills/server). Not affiliated with mcpskills.dev.
-
Updated
Jun 9, 2026 - JavaScript
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.
typescript mcp nextjs smart-contracts multi-agent-systems autonomous-agents fraud-detection ai-agents erc1155 blockchain-security vector-database payment-fraud base-l2 defi-security agent-swarm web3-security trust-scoring hnsw-index reflexion-learning crypto-fraud
-
Updated
Dec 1, 2025 - TypeScript
Structured fact memory MCP server — SQLite + FTS5, trust scoring, entity graph, auto-observe, bilingual retrieval for AI coding assistants
memory sqlite mcp persistent-memory entity-graph self-learning codex bilingual fts5 ai-memory mcp-server claude-code trust-scoring auto-observe
-
Updated
May 20, 2026 - TypeScript
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.
python git version-control developer-tools human-in-the-loop ai-agents ai-native trust-scoring tournament-mode decision-lineage
-
Updated
Feb 1, 2026 - Python
Add this topic to your repo
To associate your repository with the trust-scoring topic, visit your repo's landing page and select "manage topics."