Search results
114 packages found
Sort by: Default
- Default
- Most downloaded this week
- Most downloaded this month
- Most dependents
- Recently published
Guidance Control Plane - Compiles, retrieves, enforces, and evolves guidance rules for Claude Code sessions
- claude-flow
- claude-code
- claude
- anthropic
- ai-agent
- ai-governance
- agent-governance
- guidance
- control-plane
- policy-enforcement
- enforcement-gates
- proof-chain
- trust-system
- long-horizon
- View more
CLI tool to block --no-verify flag in git commands. Prevents AI agents from bypassing git hooks.
TITAN — TypeScript AI agent framework with multi-agent orchestration, provider routing, approval gates, receipts, evals, gateway APIs, and a React Mission Control dashboard. Open-source, MIT licensed.
- ai
- agent
- autonomous
- llm
- assistant
- automation
- chatbot
- openai
- anthropic
- gemini
- ollama
- discord
- telegram
- slack
- View more
Universal AI Agent OS — audited skills, governance rules, commands, and templates for AI coding tools (Claude Code, Cursor, Windsurf, Copilot).
- ai-agent
- mcp
- claude-code
- cursor
- windsurf
- copilot
- llm
- agent-governance
- ai-video
- skills
- prompt-engineering
- typescript
- python
- agent-skills
TypeScript client for the Vaara HTTP API: EU AI Act runtime evidence for MCP tool calls. Conformal risk scoring, policy gating, hash-chained tamper-evident audit, named detectors.
- ai
- ai-agents
- ai-governance
- agent-governance
- eu-ai-act
- compliance
- audit-trail
- risk-scoring
- conformal-prediction
- overt
- runtime-monitoring
- vaara
Minimal governance runtime for AI agents. Intercept, govern, and verify agent actions.
All terminology and labels used in AgentGuard materials are descriptive of software functionality only, not legal definitions or guarantees of compliance. Terms like receipt, audit log, evidence, audit trail, and attestation refer solely to cryptographica
- ai-agent-security
- spend-control
- model-routing
- local-first
- no-proxy
- tamper-evident
- cryptographic-attestation
- audit-log
- agent-governance
- ed25519
- llm
- ai-agents
- policy-enforcement
- openai
- View more
Open-source command center for governed AI coding agents with built-in onboarding, hard gates, MCP, and shareable run receipts.
- mcp
- model-context-protocol
- ai-coding-agents
- agent-runtime
- agent-governance
- budget-enforcement
- verifier-gates
- audit-trail
- run-receipts
- agent-receipts
- claude-code
- codex
- llmops
- cli
Rubric Claude Code adapter — long-lived loopback daemon + `rubric` CLI that routes every Claude Code tool call through the Rubric policy engine and audit log.
AI-native quality gate engine with local Bayesian learning. AST analysis, drift detection, Fix Packet generation, and agent self-healing across TypeScript, JavaScript, Python, Go, Ruby, and C#.
- ai
- llm
- ai-code-quality
- quality-gates
- static-analysis
- ast
- drift-detection
- code-review
- linter
- machine-learning
- bayesian-learning
- fix-packets
- agent-governance
- vibe-coding
- View more
Framework-neutral runtime building blocks for Rubric SDK adapters — agent identity, policy bundle polling, audit sink, and tool-call evaluator.
Opt-in policy checks, source routing, and hash-chained local audit records for AI agents
AI-native quality gates with local LLM analysis. Forces AI agents (Claude, Cursor, Copilot, Cline, Windsurf) to meet engineering standards. Bayesian Brain learns your codebase. Zero config: npx rigour-scan.
- ai
- llm
- ai-code-quality
- ai-agent
- quality-gates
- cli
- linter
- static-analysis
- security
- vibe-coding
- claude
- cursor
- copilot
- cline
- View more
Cedar policy + signed receipts for AI agent decisions. Same primitive shipping in ScopeBlind cold-chain hardware. scopeblind.com/cold-chain
- scopeblind
- mcp
- model-context-protocol
- security
- gateway
- rate-limiting
- policy
- audit
- decision-log
- tool-protection
- ai-agent
- llm-gateway
- owasp
- cedar
- View more
Structure for agentic development — durable SDLC workflows, convergence gates, agent teams, and audit trails for Claude Code
- claude-code-plugin
- sdlc
- workflow
- agent-governance
- agent-teams
- event-sourcing
- code-review
- quality-gates
- tdd
- durable-workflows
- audit-trail
Schemas and types for the Lodestar epistemic chain. Part of Lodestar, the trust layer for AI agents.
MCP server + live dashboard for AI code governance — OWASP LLM Top 10 (10/10), real-time MCP App UI, 25+ security patterns, Bayesian learning Brain, hallucinated import detection, multi-agent governance. Works with Claude, Cursor, VS Code, ChatGPT, Goose,
- ai
- llm
- mcp
- mcp-app
- mcp-server
- model-context-protocol
- ai-agent
- ai-code-governance
- owasp-llm-top-10
- bayesian-learning
- real-time-hooks
- security-patterns
- hallucinated-imports
- vibe-coding
- View more
Runtime governance adapter for PEAC interaction records with AGT mapper
- peac
- peacprotocol
- originary
- interaction-records
- signed-records
- runtime-governance
- agent-records
- agent-governance
- mcp
- a2a
- adapter
Synapse Protocol SDK - Multi-agent systems on NATS with streaming, HTTP bridges, cryptographic ACL, and reputation scoring
- synapse
- nats
- multi-agent
- agent-to-agent
- distributed-systems
- microservices
- ai-agents
- protocol
- http-bridge
- rest
- flask
- fastapi
- websocket
- browser
- View more
Infrastructure for autonomous agent economies — identity, reputation, payments, governance, discovery, coordination, and audit on Celo and Stellar. Also works fully off-chain with persistent memory, agentic loops, and tool-use.
- agent-kit
- agent-framework
- agent-memory
- agent-loop
- agentic
- ai-agents
- multi-agent
- tool-use
- obsidian
- markdown-memory
- knowledge-graph
- agent-orchestration
- agent-infrastructure
- agent-economy
- View more