AI agent tools for agent runtimes
Short answer: Our top pick for agent runtimes: flyte, with the highest AgentPick Score (82/100) among tools tagged "agent-runtime". Runners-up: brigade (77) and maka (77). Compare what each does, its license and how recently it was updated below.
| # | Tool | What it does | Score | Stars | License | Updated |
|---|---|---|---|---|---|---|
| #1 | flyte | Type-safe, distributed orchestration of agents, ML pipelines, and real-time inference on your k8s — in pure Python with async/await, also other langua… | 82/100 | ★ 7.7k | Apache-2.0 | 14 Oct 2026 |
| #2 | brigade | Brigade — Your personal intelligence, built enterprise-grade | 77/100 | ★ 11k | MIT | 12 Oct 2026 |
| #3 | maka | Apache Maka (Incubating) is a high-performance agent workspace that keeps a complete record of everything it did. | 77/100 | ★ 5.7k | Apache-2.0 | 14 Oct 2026 |
| #4 | astrid | Astrid is a portable, capability-secure operating system for composable software. | 76/100 | ★ 10k | Apache-2.0 | 14 Oct 2026 |
| #5 | ANOLISA | ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response com… | 69/100 | ★ 619 | Apache-2.0 | 14 Oct 2026 |
| #6 | celesto | Secure and persistent computer for AI agents | 68/100 | ★ 1k | Apache-2.0 | 14 Oct 2026 |
| #7 | trinity | Self-hosted AI Agents Platform supporting Claude Code, Codex, Gemini agents. Apache 2.0. | 68/100 | ★ 653 | Apache-2.0 | 14 Oct 2026 |
| #8 | fastclaw | Multi-Agent Framework | 66/100 | ★ 1.4k | See repo | 14 Oct 2026 |
| #9 | free4chat | Temporary rooms for Humans and AI Agents — run, supervise and steer Agent Tasks without a permanent workspace. | 66/100 | ★ 1.2k | MIT | 8 Oct 2026 |
| #10 | Foundry | The foundation layer for agentic intelligence. | 66/100 | ★ 873 | Apache-2.0 | 12 Oct 2026 |
| #11 | Sponsio | Deterministic safety solutions for probabilistic AI agents | 64/100 | ★ 454 | Apache-2.0 | 14 Oct 2026 |
| #12 | DashClaw | Remote approvals, policy checks, and execution evidence for unattended AI agents. | 61/100 | ★ 312 | MIT | 14 Oct 2026 |
| #13 | openclaw.net | Self-hosted Enterprise and Personal AI + agent runtime in .NET (NativeAOT-friendly) | 60/100 | ★ 522 | MIT | 14 Oct 2026 |
| #14 | 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 |
| #15 | openchatx-mcp | Turn ChatGPT into a local agent runtime. Operate your computer, use local tools, discover MCP servers, and delegate work to your own models through on… | 56/100 | ★ 261 | MIT | 13 Oct 2026 |
| #16 | AWorld | Search, understand, reproduce, and improve an idea with ease | 53/100 | ★ 1.2k | MIT | 14 Oct 2026 |
| #17 | dataagent | DataFoundry is an open-source AI workbench for data analysis, unifying data sources, knowledge, tools, and agent runtime into a governed workspace for… | 52/100 | ★ 709 | Apache-2.0 | 14 Oct 2026 |
| #18 | golf | Production-Ready MCP Server Framework • Build, deploy & scale secure AI agent infrastructure • Includes Auth, Observability, Debugger, Telemetry & Run… | 48/100 | ★ 840 | Apache-2.0 | 9 Sept 2026 |
| #19 | swarmclaw | Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory, MCP tools, schedules, delegation, and 23… | 45/100 | ★ 690 | MIT | 30 Jun 2026 |
| #20 | gini-agent | The agent that remembers and learns. | 44/100 | ★ 2k | MIT | 18 Jul 2026 |
| #21 | Hypha | Harness-oriented agent system framework for production-grade LLM agent applications | 43/100 | ★ 447 | Apache-2.0 | 4 Sept 2026 |
| #22 | task-state-guard | Reconcile stuck AI-agent tasks after restarts and timeouts. Preview SQLite changes, close stale delivery states, and never guess success. | 39/100 | ★ 859 | Apache-2.0 | 25 Aug 2026 |
| #23 | clawless | ClawLess — A serverless browser-based runtime for Claw AI Agents powered by WebContainers | 33/100 | ★ 538 | MIT | 8 Jul 2026 |
| #24 | intelligent-audit-system | AuditPilot: auditable enterprise AI agents for evidence-grounded workflows, governed tools, evaluation harnesses, human review, and remediation delive… | 25/100 | ★ 1.2k | See repo | 12 Aug 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.