InferenceIndexerInferenceIndexer.ai
/
ModelsProvidersAPIEmbedFor agentsHarnessesMethodologyAboutLoginSign Up

Agent harnesses, ranked by category

Ranked from the best-of-Agent-Harnesses list (167 harnesses, rescored weekly). Stars and licenses are facts; fit-by-category is our rubric, not a verified benchmark. Pick the harness and the model as a pair. We price the model side.

Last refreshed 2026-09-26 10:42 UTC · 87 of 167 harnesses researched in depth

Personal agentsEnterprise harnessesSmall business harnesses

Personal agents (13)

HarnessWhat it isStarsTierAutonomyRecoveryLicense
OpenClaw(opens in a new tab)Self-hosted, always-on personal agent (formerly Clawdbot/Moltbot): a gateway + event-loop runtime that treats messages, heartbeats, crons, a390,149complexheadlessresumableopen
Hermes(opens in a new tab)Nous Research's self-improving agent: a learning loop turns experience into reusable skills, builds a persistent user model across sessions,247,414slightly complexheadlessresumableopen
AnythingLLM(opens in a new tab)Self-hosted "AI second brain" **harness**: chat with your documents, run built-in agent skills (web search, code execution, browsing), and m66,253complexheadlessresumableopen
nanobot(opens in a new tab)Ultra-lightweight, self-hosted personal agent framework: the **harness** is a Python daemon wiring tools, memory, and MCP into chat/webhook 48,409mostly simplen/an/aunknown
CowAgent(opens in a new tab)Self-hosted **harness** (formerly chatgpt-on-wechat) that plans tasks, runs tools/skills, and self-evolves via memory; multi-model, multi-ch47,053slightly complexn/an/aunknown
Khoj(opens in a new tab)Self-hostable "AI second brain": answers over your docs and the web, custom agents, scheduled automations, and multi-client reach (web, Obsi37,429complexheadlessresumableopen
Eliza(opens in a new tab)Open "agentic operating system" (elizaOS): persistent multi-agent runtime with character files, a plugin ecosystem, and social/platform inte19,395complexheadlessresumableopen
Agent Zero(opens in a new tab)Organic, prompt-defined personal agent framework: hierarchical sub-agents, persistent memory, browser and code tools, and self-modifying beh19,216slightly complexboundedresumableunknown
OpenHarness (HKUDS)(opens in a new tab)Open agent harness with a built-in personal agent ("Ohmo") that runs across Feishu, Slack, Telegram, and Discord; core tool-use, skills, mem15,810complexboundedresumableopen
QM(opens in a new tab)Y Combinator's multiplayer agent **harness** for work, open-sourced from months of internal use: every person and room gets scoped memory, f15,181complexheadlessdurableopen
OpenJarvis(opens in a new tab)Stanford Hazy Research's local-first personal AI **harness**: on-device model inference (Ollama built in), agent execution, memory, and lear10,019slightly complexheadlessnoneopen
AIlice(opens in a new tab)Fully autonomous general-purpose agent; one binary, Docker-ready, for when you want "set goal and walk away" without a framework.1,417slightly complexboundednoneopen
Talon(opens in a new tab)Multi-platform personal agent living in Telegram, Discord, Teams, and the terminal. The **harness** is a pluggable-backend loop (Claude, Kil83slightly complexheadlessresumableopen

Enterprise harnesses (18)

HarnessWhat it isStarsTierAutonomyRecoverySandboxingLicense
Codex(opens in a new tab)OpenAI's terminal coding agent. The **harness** is the sandboxed tool-call loop with multi-provider support; the CLI is the shell. Reference125,493slightly complexboundedresumablestrongopen
Open Interpreter(opens in a new tab)Lightweight terminal coding agent oriented to open models (DeepSeek, Kimi, Qwen). The **harness** is a code-execution loop — the model write68,390mostly simpleboundedresumablestrongopen
autogen(opens in a new tab)Conversable agents and group chats; code execution and human-in-the-loop; Microsoft origin, AG2 ecosystem. ⚠️ In maintenance mode since late61,079complexboundedresumablestrongopen
langgraph(opens in a new tab)State-machine graphs over LLM steps; checkpointing, human-in-the-loop, and durable execution so workflows survive restarts.42,015slightly complexheadlessdurablebasicopen
Khoj(opens in a new tab)Self-hostable "AI second brain": answers over your docs and the web, custom agents, scheduled automations, and multi-client reach (web, Obsi37,429complexheadlessresumablestrongopen
deepagents(opens in a new tab)LangChain's Python+TypeScript agent harness on top of LangGraph: planning tool, virtual filesystem, shell sandbox, sub-agent spawning—the "C29,596slightly complexboundeddurableunknownopen
openai-agents-python(opens in a new tab)Handoffs, guardrails, and multi-LLM routing; minimal surface so you own the loop.29,582mostly simpleboundedresumablestrongopen
letta(opens in a new tab)Python agent runtime with tool use and control flow; lean API; stateful agents with long-horizon memory.24,809mostly simpleheadlessdurablebasicopen
Google ADK(opens in a new tab)Google's official Agent Development Kit: code-first Python toolkit for building, evaluating, and deploying agents. Optimized for Gemini but 21,581complexheadlessresumablestrongopen
SWE-agent(opens in a new tab)LM-driven harness built for SWE-bench: edit state, command execution, and issue-focused loop—the reference agent stack next to the benchmark20,370slightly complexheadlessresumablestrongopen
pydantic-ai(opens in a new tab)Type-safe Python agents with Pydantic I/O; multi-provider, MCP, Logfire observability, and human-in-the-loop.20,072slightly complexboundeddurableunknownopen
OpenHarness (HKUDS)(opens in a new tab)Open agent harness with a built-in personal agent ("Ohmo") that runs across Feishu, Slack, Telegram, and Discord; core tool-use, skills, mem15,810complexboundedresumablestrongopen
QM(opens in a new tab)Y Combinator's multiplayer agent **harness** for work, open-sourced from months of internal use: every person and room gets scoped memory, f15,181complexheadlessdurableunknownopen
Cloudflare Agents(opens in a new tab)Persistent, stateful agents on Durable Objects: state, websockets, scheduling, and AI chat baked in. The serverless answer to "where does th5,609slightly complexheadlessdurableunknownopen
AgentStack(opens in a new tab)Scaffolds full agent projects; plugs in CrewAI, LangGraph, OpenAI Swarm, LlamaStack and wires AgentOps observability from day one.2,191slightly complexn/an/astrongopen
langgraph-bigtool(opens in a new tab)Build LangGraph agents with large tool sets; retrieval and on-demand tool loading so agents scale beyond context without stuffing every sche558slightly complexboundeddurablenoneopen
Proliferate(opens in a new tab)Open-source AI IDE for Claude Code, Codex, OpenCode, and more. The **harness** contribution is the workspace/session orchestration layer: ru505complexboundedresumablestrongopen
AgentBox(opens in a new tab)Runs multiple coding agents in parallel, each in its own sandboxed VM, locally or in the cloud, from one command. The **harness** contributi467slightly complexn/an/astrongopen

Small business harnesses (12)

HarnessWhat it isStarsTierAutonomyRecoveryBuild vs buyLicense
Open Interpreter(opens in a new tab)Lightweight terminal coding agent oriented to open models (DeepSeek, Kimi, Qwen). The **harness** is a code-execution loop — the model write68,390mostly simpleboundedresumableblueprintopen
LiteLLM(opens in a new tab)One interface to 100+ LLMs; routing, caching, budgets. Not an agent framework—the pipe every agent framework uses.59,233mostly simplen/aretryunknownopen
nanobot(opens in a new tab)Ultra-lightweight, self-hosted personal agent framework: the **harness** is a Python daemon wiring tools, memory, and MCP into chat/webhook 48,409mostly simplen/an/aunknownunknown
openai-agents-python(opens in a new tab)Handoffs, guardrails, and multi-LLM routing; minimal surface so you own the loop.29,582mostly simpleboundedresumablebuildopen
smolagents(opens in a new tab)Code-as-action agents: model outputs Python executed in sandbox (E2B, Modal, etc.); ~1k LOC core.29,413mostly simpleboundednoneunknownopen
letta(opens in a new tab)Python agent runtime with tool use and control flow; lean API; stateful agents with long-horizon memory.24,809mostly simpleheadlessdurableblueprintopen
botpress(opens in a new tab)Visual bot builder and runtime; multi-channel, open-source alternative to commercial bot platforms.14,919complexheadlessresumablemanagedopen
PraisonAI(opens in a new tab)Autonomous multi-agent teams with a single entry point; emphasis on minimal config.9,080mostly simpleboundednoneblueprintopen
strands-agents(opens in a new tab)Model-driven Python SDK; decorators for tools, native MCP, multi-agent; "minimal code" without sacrificing provider choice.7,377mostly simpleboundedresumableunknownopen
youtu-agent(opens in a new tab)Tencent Cloud's agent framework: a minimal tool-calling **harness** designed to perform well with open-source models, positioned as a lighte4,614mostly simpleboundedretryblueprintunknown
AgentSilex(opens in a new tab)~300 lines of readable agent code on top of LiteLLM; the "I want to see the whole loop" option for learning or minimal production.456super simpleboundednonebuildopen
SuperAgentX(opens in a new tab)Lightweight multi-agent orchestrator with an AGI-angle; minimal surface, docs-first, for teams that want orchestration without the kitchen s203mostly simpleboundednoneblueprintopen
How the derived tables are filtered

Enterprise harnesses

Include if the license signal is open-source AND at least one of: strong sandboxing (container/VM/OS-level isolation) or durable recovery (execution state survives restarts).

Small business harnesses

Include if the harness is a runnable runtime (not a skill pack, curated list, benchmark suite, or observability tool) AND either managed (buy, not build) or simple to adopt (installable without a platform team), AND at least 100 GitHub stars.

Personal agents

Direct category: always-on, self-hosted agents run as a daemon and talked to from chat apps. No filter.

A research-harness table is prepared but withheld: the source list is still thin. It releases when the category grows.

Full rubric wording: Methodology, Harness Tables.

Data: best-of-Agent-Harnesses (https://ryanalberts.github.io/best-of-Agent-Harnesses/), CC-BY-SA-4.0 · CC-BY-SA-4.0. Fit-by-category is InferenceIndexer's rubric applied to that data; stars and licenses are the source's facts.

Continue: For agents · Model rankings · API docs

InferenceIndexerInferenceIndexer.ai · Inference Recommendation Engine
ProvidersModel TypeMethodologyAPI DocsFor AgentsHarnessesData QualityAboutPrivacy PolicyTerms of Service@inferenceindex
676 models · 75 providers