# AI Agent Tools With Open-Weight Model Support

> Source: https://theagentsindex.com/collections/ai-agent-tools-with-open-weight-model-support (curated, quality-gated, re-verified)

Being "model-agnostic" and supporting an open-weight model are different claims, and this collection only counts the second one: a tool is listed here because its own published listing names a specific open-weight family (Llama, Mistral, DeepSeek, Qwen, GLM or Kimi among them), or explicit local execution through a runtime like Ollama or LM Studio. 24 of the 144 tools in this index clear that bar.

Several tools that look like candidates fail on exactly that distinction rather than on capability. [LangChain](/langchain) describes its model support as "Model-agnostic (any LLM)", [Vapi](/vapi) as "Model-agnostic (bring your own)", [Retell AI](/retell-ai) as "Model-agnostic (choose your LLM)", and [LangGraph](/langgraph) names "OpenAI, Anthropic, Google, and more", which is three closed providers and an "and more". Each of the four may well run an open-weight model; nothing any of them publishes says so, so none of them is counted here.

By category: 5 of 16 [agent frameworks](/category/frameworks) (Microsoft Agent Framework, Pydantic AI, Agno, Google ADK, CrewAI), 8 of 28 [coding agents](/category/coding-agents) (Cline, Aider, Juggler, OpenAI Codex CLI, OpenCode, Zot, Zed and Junie, which JetBrains' own docs confirm can point at a local Ollama or LiteLLM runtime alongside its frontier-model options), 8 of 32 [agent platforms](/category/agent-platforms) (n8n, Dify, Botpress, OpenClaw, Vecbase), 3 of 23 [voice agents](/category/voice-agents) (ElevenLabs Conversational AI, Deepgram Voice Agent API, Cartesia) and 3 of 13 [research agents](/category/research-agents) (GPT Researcher, Perplexity and Genspark). Genspark is the one entry where the open-weight model is the vendor's choice rather than yours: its Super Agent blends nine LLMs, DeepSeek among them, and you do not pick which one answers. Everywhere else on this page the open weights are something you select, host or point the tool at.

Our remaining categories have no entry here at all: [support agents](/category/support-agents), [sales & marketing agents](/category/sales-marketing-agents) and the newer [agent tools](/category/agent-tools). Every listing in all three is closed-model and cloud-only by its own published record.

| Name | What it is | Why it's here | Pricing | API |
| --- | --- | --- | --- | --- |
| [Microsoft Agent Framework](https://theagentsindex.com/microsoft-agent-framework.md) | Open-source .NET, Python and Go SDK for building AI agents and graph-based multi-agent workflows. | Builds an agent from Azure OpenAI, OpenAI, Microsoft Foundry, Anthropic Claude, local models via Ollama or a custom provider: genuinely model-agnostic despite the Microsoft branding. | — | Yes |
| [Pydantic AI](https://theagentsindex.com/pydantic-ai.md) | Open-source Python agent framework from the Pydantic team, with a typed agent loop and swappable models. | Model-agnostic across OpenAI, Anthropic, Gemini, Mistral, Cohere, DeepSeek, Grok, Bedrock and local models via Ollama: one of the widest named provider lists in this collection. | — | Yes |
| [Agno](https://theagentsindex.com/agno.md) | Python SDK, open-source AgentOS runtime and hosted control plane for building and operating agents. | Interchanges 20+ LLM providers including Ollama for local models without rewriting agent code, and a free AgentOS Control Plane runs entirely on your own machine for local development. | — | Yes |
| [Google Agent Development Kit (ADK)](https://theagentsindex.com/google-adk.md) | Open-source framework for building, evaluating and deploying AI agents in Python, TypeScript, Go, Java or Kotlin. | Optimized for Gemini but genuinely model-agnostic through a LiteLLM integration: OpenAI, Anthropic Claude, Cohere, local Ollama models and 100+ other providers are all reachable the same way. | — | Yes |
| [CrewAI](https://theagentsindex.com/crewai.md) | Open-source multi-agent framework with a managed platform for deploying and governing agent workflows. | Its integrations list routes through LiteLLM to providers beyond the OpenAI, Gemini and Hugging Face options it names directly, reaching local and self-hosted models via Ollama. | — | Yes |
| [n8n](https://theagentsindex.com/n8n.md) | Workflow automation platform for building and running AI agents on a visual canvas, with code where needed. | Its native AI-agent and LLM nodes list OpenAI, Anthropic, Ollama and more: wire a local Ollama model into the same visual canvas as any hosted provider. | — | Yes |
| [Dify](https://theagentsindex.com/dify.md) | Open-source platform for building agentic workflows, AI agents and RAG knowledge pipelines. | Integrates hundreds of LLMs from dozens of providers, explicitly including open and local models alongside OpenAI, Anthropic and Google, so a node can be swapped to a self-hosted model without rebuilding the flow. | — | Yes |
| [Botpress](https://theagentsindex.com/botpress.md) | AI agent platform with a visual studio, a code-first TypeScript ADK and a helpdesk, priced per conversation. | Model-agnostic across OpenAI, Anthropic Claude, Google Gemini and open-weight models, per its own published spec. | — | Yes |
| [Cline](https://theagentsindex.com/cline.md) | Open-source coding agent for VS Code, JetBrains, the terminal and CI, running on whichever model you bring. | Bring-your-own-key across Anthropic, OpenAI, DeepSeek, xAI, Mistral, Cerebras or a local model via Ollama, plus a paid ClinePass tier for discounted access to a curated set of open-weight models (Qwen, DeepSeek, Kimi, GLM and others). | — | Yes |
| [Aider](https://theagentsindex.com/aider.md) | Open-source terminal AI pair programmer that edits files in your local git repo and commits the changes. | Bring-your-own-key and model-agnostic across Anthropic, OpenAI, DeepSeek, local models and effectively any LLM via Ollama: free either way, since you pay the model provider directly. | — | Yes |
| [Juggler](https://theagentsindex.com/juggler.md) | Visual workbench for AI coding agents: branching conversation trees, inspectable model transactions, local or remote. | Drives Claude, OpenAI, Gemini, Ollama, OpenRouter or DeepSeek models through a swappable JavaScript plugin system: free, open-source and model-agnostic with no usage cap of its own. | — | No |
| [Codex CLI](https://theagentsindex.com/codex-cli.md) | OpenAI's terminal coding agent for inspecting, editing and running repository code from the shell. | Ships built-in support for local/self-hosted models via Ollama and LM Studio alongside Amazon Bedrock and OpenAI's own models: any other provider needs a manual config.toml entry. | — | Yes |
| [OpenCode](https://theagentsindex.com/opencode.md) | Open source AI coding agent for the terminal, desktop app and IDE, with 75+ model providers. | Bring any of 75+ model providers, including your own local Ollama models, reachable through Models.dev or wired in directly via the /connect command. | — | Yes |
| [zot](https://theagentsindex.com/zot.md) | Single-binary terminal coding agent harness in Go, with 30+ model providers and any-language extensions. | Connects to 30+ model providers (Anthropic, OpenAI/Codex, Gemini, Kimi, DeepSeek, GitHub Copilot, Bedrock, OpenRouter and local Ollama models) through one static Go binary. | — | Yes |
| [Zed](https://theagentsindex.com/zed.md) | Rust-based code editor with a built-in agent panel, ACP external agents and Zed-hosted models. | Connects to ten-plus model providers including Mistral, DeepSeek, Ollama and LM Studio, and ships its own first-party open-weight Zeta2 model for inline edit prediction, included in every plan. | — | Yes |
| [ElevenLabs Agents](https://theagentsindex.com/elevenlabs-conversational-ai.md) | Hosted platform for building voice and chat agents, with telephony, SDKs and a choice of LLM. | An OpenAI-compatible custom endpoint opens the door to open-source models like Llama 3.3 or DeepSeek R1 via hosts such as Cloudflare Workers AI, Groq or Together AI, alongside the built-in OpenAI, Anthropic and Google options. | — | Yes |
| [Deepgram Voice Agent API](https://theagentsindex.com/deepgram-voice-agent-api.md) | One WebSocket API that runs speech-to-text, LLM orchestration and text-to-speech for real-time voice agents. | Its LLM layer spans OpenAI, Anthropic, Google, NVIDIA, Groq and Amazon Bedrock: more than 30 specific models, including open-weight options such as Groq's gpt-oss-20b and NVIDIA's Nemotron-3-Nano alongside closed frontier models. | — | Yes |
| [Cartesia](https://theagentsindex.com/cartesia.md) | Real-time speech models and a managed runtime for production phone and web voice agents. | The Line SDK connects to more than 100 LLM providers via LiteLLM, including open-weight models by name, rather than locking a buyer into Cartesia's own reasoning layer. | — | Yes |
| [GPT Researcher](https://theagentsindex.com/gpt-researcher.md) | Open-source autonomous research agent that writes cited long-form reports from web and local sources. | Model-agnostic: drive it with OpenAI, Anthropic, Google, Groq or local Ollama models, pairing whichever LLM you choose with a search back-end like Tavily or Bing. | — | Yes |
| [Junie](https://theagentsindex.com/junie.md) | JetBrains coding agent for the terminal, JetBrains IDEs and CI, running on hosted or your own model keys. | JetBrains' own docs confirm Junie can point at a local runtime via Ollama or LiteLLM alongside its OpenAI/Anthropic/Google frontier-model options: a genuine open-weight path, not just "model-agnostic" marketing language. | — | Yes |
| [OpenClaw](https://theagentsindex.com/openclaw.md) | Open-source personal agent runtime you host yourself and message from any chat app. | Routes requests through 64 model and media providers including local runtimes (Ollama and LM Studio) alongside Anthropic, Google and OpenAI, plus gateways such as Amazon Bedrock and OpenRouter. | — | Yes |
| [Vecbase](https://theagentsindex.com/vecbase.md) | Annual membership for member-rate access to a multi-vendor model catalog, plus hosted AI agents. | Agents switch between multiple underlying models (Claude, GPT and Gemini beside the open-weight Kimi and DeepSeek), with transparent per-token billing on whichever one you pick. | — | Yes |
| [Perplexity](https://theagentsindex.com/perplexity.md) | AI answer engine with an agentic Computer, the Comet browser, and a developer API for web-grounded search. | Names z.ai's GLM and Moonshot AI's Kimi, both added in 2026, alongside its own Sonar models and GPT, Claude and Gemini: the open-weight options are selectable, not just routed to behind the scenes. | — | Yes |
| [Genspark](https://theagentsindex.com/genspark.md) | All-in-one AI workspace with autonomous agents for slides, docs, sheets, code, media and scheduled automation. | Its Super Agent blends nine specialized LLMs including DeepSeek: the one entry here where the open-weight model is chosen by the vendor's router rather than by you. | — | Yes |

## How this list is built

A tool earns a place here only if its own Published, sourced listing names at least one specific open-weight model family (Llama, Mistral, DeepSeek, Qwen, GLM, Kimi or similar) or explicit local-model execution (Ollama, LM Studio, "local model") somewhere in its `whatIs`, `whatItDoes`, `keyFeatures`, `integrations` or `attributes.modelLLM` fields: a generic "model-agnostic" or "bring your own model" claim with no open-weight option ever named does not qualify on its own. Verified directly against each listing's own text, not inferred from the `open-models` tag alone in either direction: a tagged listing that names nothing specific is excluded, and an untagged listing whose own text clears the bar is included.

Re-derived against the live corpus on 2026-08-27: 24 entries still Published, 0 dead, every per-entry note still matches its listing's current text, and no facts have moved since the 2026-08-26 pass. Candidates with an open-weight claim in their public listing but not listed here were checked and held back for the same reason as on 2026-08-26: page_context does not return the listing fields that gate open-weight admission (`whatIs`/`integrations`/`modelLLM`) and the listings lane owns that decision, so adding on a stale-reason cycle without that join is still the wrong call.