skillhub
Self-hosted, open-source agent skill registry for enterprises. Publish & version skill packages, govern with RBAC and audit logs, deploy on-premise with Docker or Kubernetes.
- 5.4k
- Java
- Apache-2.0
- 10 h ago
Self-hosted, open-source agent skill registry for enterprises. Publish & version skill packages, govern with RBAC and audit logs, deploy on-premise with Docker or Kubernetes.
Open-source AI agent governance. Write the rules declaratively, Bernstein enforces them and produces the verifiable, replayable record. Free, Apache-2.0. https://bernstein.run
Self-hosted AI API and MCP gateway for organizations: SSO and RBAC, per-user identity for MCP tool calls, PII redaction and tool-call guards, rate limits, budgets, cost accounting and audit logs.
Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.
Deterministic Operating System, Safety Kernel, and Causal Nervous System for AI Agents.
Enterprise admin platform in Go on go-kratos (Ent): Protobuf as the single API contract with full-stack codegen (Go APIs + TypeScript clients, one-click CRUD scaffolds), multi-tenant RBAC (Casbin / OPA / Zanzibar), TOTP MFA, 180-day audit logging aligned with China MLPS 2.0 (等保) — with Vue3 (Vben / Element Plus) and React 19 (Antd) frontends.
MCP server for SSH: let Claude Code, Codex and any MCP client run commands, transfer files and manage servers over SSH, with human approval, an encrypted vault and a live audit trail. Desktop app and CLI included.
HIPAA-compliant browser for AI agents: an AI browser on desktop, agentic browsers in the cloud, every action audited.
An AI that administers Linux through typed, approval-gated, Ed25519-audited actions. The model selects the action; the daemon builds the command.
A set of curated exercises to help you prepare for the CKS exam
🧠 给 AI 一个可信的第二大脑:本地 SQLite · 先审核再入库 · 不可篡改审计 · 记忆账本。🕷 蜘蛛侠皮肤 · 🔍 自建集 R@5 99.1% / LongMemEval-S 97.2% · 🧩 一个库接入 DSH / Claude Code / Codex / Cursor / 任意 MCP · ⭐ MIT 开源 · 🚀 零依赖开箱即用
Audit trail database for AI agents. Tamper-evident, checksum-backed decision logs with session replay and time-travel debugging to support EU AI Act Article 12 record-keeping. Drift detection, MCP, Python & TypeScript SDKs. Self-host or cloud.
Compartment is a self-hosted deployment system for small software on infrastructure your team controls.
Collect / retrieve Office365, AzureAD and DLP audit logs and output to PRTG, Azure Log Analytics Workspace, SQL, Graylog, Fluentd, and/or file output.
Audit your GitHub Actions workflow runs to see exactly which Actions were downloaded
Open-source (MIT) event sourcing database and processing runtime — Orleans-based kernel, pluggable storage (MongoDB, PostgreSQL, SQL Server, SQLite), and language-agnostic gRPC clients for .NET, TypeScript, Kotlin/Java, and Elixir (Python coming soon).
Proxmox VE 8.x/9.x 自托管管理面板:虚拟机与 LXC 容器全生命周期、cloud-init 模板流水线、 监控大盘、VNC/串口控制台、多角色权限与操作审计;另含 AI 排查助手(会话式归因、要改系统的 命令逐条批准、Token 用量统计)、SSH 防暴力破解、端口异常检测与安全基线加固。 A self-hosted web panel for Proxmox VE — VMs, LXC, cloud-init, monitoring, RBAC, audit, and an AI inspection assistant.
Activity logs and audit trail for Symfony, stored in Elasticsearch or your relational database
Micro-VM sandbox for AI agents: isolated, gated and auditable, to prove what your agents did
Local-first MCP policy proxy. Tool-block, SQL-mutation gate, PII redact, audit, rate-limit, OpenTelemetry, vault secrets, first-use quarantine, schema pre-inject. No hosted gateway. One YAML Lens wraps any MCP, 20 included (Postgres, MySQL, MongoDB, GitHub, Stripe, Snowflake, etc.). 84% fewer tokens, ~3x faster, holds PII leaks. AGPL or commercial.
Run SQL on production databases with approval and a full audit. Users submit from Slack or a web IDE, and a DBA approves. QueryHub runs the approved query with a read, write or DDL login and masks personal data. PostgreSQL, SQL Server, ClickHouse and Athena.
LLM proxy with built-in DLP and regulatory compliance. Redacts secrets before they reach the API. EU AI Act, GDPR, HDS/PCI DSS ready. Multi-provider failover, live TUI, virtual keys, fan-out. 6 MB, zero deps. Rust.
The open-source safety layer for AI agents — block unsafe tool calls, require approval, enforce budgets, audit, replay.
Local-first agentic software factory. Agents file tasks, Orbit lands them from sandboxed worktrees, and every step is audited. Works with Claude Code, Codex, Grok, Agy and Muse. No telemetry.
TypeScript SDK for the NitroPing audit log — batching client, error capture, Hono/Express/Nitro adapters, and GenAI cost tracing.
world-model-mcp is a signed audit memory server for AI coding agents, delivered as an MCP tool. Every event Ed25519-signed and Merkle-chained; offline-verifiable against pinned public keys. Hosted platform with hybrid post-quantum signing at etch.systems.
Auth for AI agents and humans. First-class agent identity, MCP OAuth 2.1, delegation, audit. TypeScript, edge-native, MIT.
Give AI assistants access to Postgres with per-user permissions and human approval for writes.
Enterprise admin platform in Rust on the RushWind framework (axum + SeaORM): Protobuf as the single API contract with build-time codegen (203 routes, zero hand-written), multi-tenant RBAC, TOTP MFA, 180-day audit logging aligned with China MLPS 2.0 (等保) — with Vue3 (Vben / Element Plus) and React 19 (Antd) frontends.
Unified entity change events (insert/update/delete with old and new values) across JPA providers (Hibernate, EclipseLink).
Integrate spatie/laravel-event-sourcing v7 with Filament v4: write through aggregates, browse stored events, and replay projectors.
The missing observability layer for AI agents. Real-time session visualization. Every prompt. Every tool call. Every model switch. Live. Drop-in OpenAI/Anthropic gateway. Self-hosted. Bun + SQLite.