Search results for "audit"
The open agent control plane. Govern autonomous AI agents with pre-execution policy enforcement, approval gates, and audit trails. Works with LangChain, CrewAI, MCP, and any framework.
Framework for AI Backend. Build and run AI agents like microservices - scalable, observable, and identity-aware from day one.
ToolHive is an enterprise-grade platform for running and managing Model Context Protocol (MCP) servers.
An open-source Agent-first Identity and Access Management (IAM) /LLM MCP & agent gateway and auth server with web UI supporting OpenClaw, MCP, OAuth, OIDC, SAML, CAS, LDAP, SCIM, WebAuthn, TOTP, MFA,
Run a fleet of AI agents on Kubernetes. Administer your cluster agentically
A modular MCP server that provides commonly used developer tools for AI coding agents
Nornicdb is a low-latency, Graph + Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and writes. Uses Neo4j Bolt/Cypher and qdrant's gRPC drivers so you can switch with no changes. T
Kelos - The Kubernetes-native framework for orchestrating autonomous AI coding agents.
Beads - A memory upgrade for your coding agent
Privacy-first LLM proxy and AI gateway — load balancing, multi-provider routing, API key management, usage tracking, rate limiting. Self-hosted. Zero knowledge of your prompts.
AI-native HTAP database with Git-for-Data and built-in vector search, serving as the data and memory backbone for intelligent agents and applications.
Security scanner for AI-generated ("vibe-coded") code. Runs SAST, DAST, and sandboxed exploit simulation across 15+ languages using 30+ tools. Catches what LLMs introduce before it ships — wit
A selective learning and memory substrate for agentic systems — typed, revisable, decayable memory with competence learning and trust-aware retrieval.
An API server that implements the official MCP Registry API, providing standardised access to MCP servers from multiple backends, including file-based and other API-compliant registries.
Open-source, self-improving autonomous agent swarm🐇
High-performance zero-dependency L4/L7 load balancer written in Go. Single binary with Web UI, clustering, MCP/AI integration. 8.5K RPS, 39 E2E tests.
Your AI forgets everything between sessions. SAME fixes that. Local-first, no API keys, single binary.
A universal CLI for Weaviate, Milvus, Chroma, Qdrant, and other vector DBs to help view, list, create, delete, and search collections and documents in collections for development, test, and debugging
Artifical Ecology For Thought and Emergent Reasoning. The Colony That Builds With You.
OpenClaw. open claw. Alternative to openclaw. WhatsApp bot. Telegram bot. Slack bot. Desktop bot. Whatsappbot,telegrambot,slackbot, consolebot,clibot,mcpbot
Run AI coding agents in hardened container sandboxes.
A deterministic development harness for Claude Code — MCP workflow engine, enforcement hooks, YAML workflows, and multi-agent consensus (Claude + Codex + Gemini)
ZimaOS Blue - A Local-First Agent Runtime for Bold Builders. Out-of-the-Box, Open-Source, Universal, Vendor-Neutral
🛡️ Enable secure, read-only SSH access for LLM agents to audit servers, run diagnostics, and inspect logs without risking data changes.
Autonomous local AI assistant in Go — 40+ tools, 20+ LLM providers, multi-agent orchestration, self-improving
An open-source SSPM tool written in Go
🛡 Enforce security policies, redact data, sandbox processes, and verify integrity for Model Context Protocol (MCP) server communication.
Self-hosted AI workflow orchestration server. Runs multi-phase LLM pipelines (Director → Architect → Implementer → QA) and delivers structured artifacts via PR, webhook, or bundle.