AI agent tools for AI infrastructure
Short answer: Our top pick for AI infrastructure: skillhub, with the highest AgentPick Score (78/100) among tools tagged "ai-infrastructure". Runners-up: harnessrouter (75) and tensorlake (70). Compare what each does, its license and how recently it was updated below.
| # | Tool | What it does | Score | Stars | License | Updated |
|---|---|---|---|---|---|---|
| #1 | skillhub | Self-hosted, open-source agent skill registry for enterprises. Publish & version skill packages, govern with RBAC and audit logs, deploy on-premise wi… | 78/100 | ★ 5.2k | Apache-2.0 | 14 Oct 2026 |
| #2 | harnessrouter | HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI,… | 75/100 | ★ 3k | Apache-2.0 | 14 Oct 2026 |
| #3 | tensorlake | Tensorlake is a serverless runtime for sandboxes and deploying background agentic applications | 70/100 | ★ 1k | Apache-2.0 | 14 Oct 2026 |
| #4 | caura | Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit tr… | 67/100 | ★ 497 | Apache-2.0 | 14 Oct 2026 |
| #5 | paritok-4b-v1 | Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more … | 65/100 | ★ 1.5k | Apache-2.0 | 6 Oct 2026 |
| #6 | DashClaw | Remote approvals, policy checks, and execution evidence for unattended AI agents. | 61/100 | ★ 312 | MIT | 14 Oct 2026 |
| #7 | homelab-monitor | Plug-and-play homelab dashboard in one container — GPU, local-AI VRAM, Docker, systemd, host health. Built-in read-only MCP server so AI agents can ex… | 61/100 | ★ 219 | MIT | 14 Oct 2026 |
| #8 | sandbase-harness | Local-first, self-hosted AI agent runtime and MCP bridge with sandboxed sessions, memory, credentials, audit/replay, and a local Console. | 57/100 | ★ 639 | Apache-2.0 | 12 Oct 2026 |
| #9 | LongMemory | Local persistent memory store for LLM applications including claude desktop, github copilot, codex, antigravity, etc. | 48/100 | ★ 4.5k | Apache-2.0 | 20 Sept 2026 |
Source: each project's public GitHub repository (description, stars, license, last push). Listed tools aren't tested or ranked by AgentPick.
How to choose
- Grant the narrowest permissions the server allows.
- Check whether it runs locally or calls a remote service.
- Prefer servers listed in the official MCP registry.
Get the best new agent tools every week. Free, with a verdict on each. Get the weekly digest
Related
AI agent tools for local-first setups →
MCP servers
AI agent tools for knowledge graphs and bases →
MCP servers
AI agent tools for RAG (retrieval-augmented generation) →
MCP servers
AI agent tools for MCP client →
MCP servers
AI agent tools for cybersecurity →
MCP servers
AI agent tools for DevOps →
MCP servers
AgentPick Weekly
The week's new agent tools with a verdict on each, every week. Free. We'll email you a link to confirm, and you can unsubscribe any time. See our Privacy Policy.