Run the agent loop on a local or self-hosted model
No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.
What counts as done
The harness completes a small multi-file edit with the local model, and no request leaves the machine.
Measured, for our own tests: every tool call is executed rather than printed as text. No docs we read state these figures, so they don't count against a listing here.
How agents ask for it: use my llama-server with the agent
, run the coding agent on Qwen locally
, no cloud, everything stays on this machine
, point it at LM Studio
Does the job, with a limit 24
It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.
| Listing | Why |
|---|---|
| Agent Zero D Agent Zero, s.r.o. | The setup has a local model server as a provider and the agent runs in its own container, but whether the container's own update or telemetry traffic leaves the machine was not established. source |
| Aider D Aider AI LLC | Ollama, LM Studio and OpenAI-compatible APIs are documented and edits use text formats rather than tool calls, but the update check pings by default until --no-check-update. source |
| AXLR BB Underpass AI | local_models lists llama-server and vLLM entries that must return native tool_calls, and OPENROUTER_API_KEY becomes optional, but the engine updater and catalog fetches still reach api.github.com and the registry. source |
| Clawboo B Sanreds | Since 0.6.0 Clawboo Native runs on a local Ollama with no key and marks models that cannot use tools, but Claude Code, Codex and Hermes teammates still call their own vendors. source |
| Cline C Cline Bot Inc. | Ollama and LM Studio are listed providers and -P selects them, but telemetry is on by default and must be turned off with telemetryOptOut before the first task. source |
| Crush D Charmbracelet, Inc. | provider add ollama --type ollama --base-url and model add register local models, and any OpenAI-compatible server works, but usage metrics are sent by default until CRUSH_DISABLE_METRICS=1 or DO_NOT_TRACK=1. source |
| Pi B Earendil Inc. | models.json takes a compatible endpoint with a baseUrl and api type, but the pages read name no Ollama or llama.cpp preset, and the install ping and version check leave the machine unless PI_OFFLINE is set. source |
| GitHub Copilot CLI C GitHub, Inc. | A BYOK provider registry file and local Ollama models are supported, but a Copilot sign-in may still be required and client telemetry is on until --disable-client-telemetry. source |
| goose BB Agentic AI Foundation (Linux Foundation) | GOOSE_PROVIDER with GOOSE_PROVIDER__HOST points at a custom endpoint and Ollama is a provider, but Ollama unloading models closed MCP transports (acc-18) and usage data is sent until turned off. source |
| Junie CLI D JetBrains s.r.o. | Custom model profiles take an Ollama localhost baseUrl or any OpenAI-compatible or Anthropic endpoint, but the headless page says a Junie token is required, and the anonymous statistics default is unstated. source |
| Kilo Code CLI BB Kilo Code Inc. (the terms are a contract with Anaconda, Inc. on behalf of itself and its affiliates, including Kilo Code Inc.) | Any provider/model with your own key or a local model needs no Kilo account, but PostHog telemetry with the conda client ID is on until turned off. source |
| Kimi Code CLI C Moonshot AI (the global Kimi terms name NOVASCENT PRIVATE LIMITED, Singapore) | `openai`-type providers take any `base_url`, so llama-server or LM Studio work, but anonymous telemetry and the update preflight are on by default until `KIMI_DISABLE_TELEMETRY=1` and `KIMI_CODE_NO_AUTO_UPDATE=1` are set. source |
| Letta B Letta | `--backend local` with Ollama, LM Studio and llama.cpp keeps agent state on the machine, but telemetry and the auto-updater stay on until `LETTA_CODE_TELEM=0` and `DISABLE_AUTOUPDATER=1`. source |
| mini-swe-agent B No legal entity named. The MIT licence names Kilian A. Lieret and Carlos E. Jimenez | Any LiteLLM model works, but a local model needs `MSWEA_COST_TRACKING=ignore_errors` and the docs say that disables spend management. source |
| MiniMax Code B Nanonoble Pte. Ltd. | `mcode provider add` takes any `openai-completions` or `anthropic-messages` base URL, but the pages read do not say whether telemetry or update checks stay on. source |
| Mistral Vibe CLI B Mistral AI (RCS Paris 952 418 325) | Any OpenAI-compatible endpoint works through the `llamacpp` preset or `api_base`, but telemetry and update checks are on by default and must be disabled in `config.toml`. source |
| OpenAI Codex BB OpenAI OpCo, LLC | `--oss` with `oss_provider = ollama|lmstudio` and custom `model_providers.<id>.base_url` run local models, but analytics and feedback collection are on until `analytics.enabled = false`. source |
| OpenCode BB Anomaly Innovations, Inc. | Ollama is probed at `127.0.0.1:11434` and any OpenAI-compatible `baseURL` works; acc-24 passed five tasks on LM Studio, but the default `notify` update check still leaves the machine. source |
| OpenHands BB All Hands AI | LM Studio, Ollama, vLLM and SGLang are documented with a recommended local model, but the page warns local models often fail tool calls and PostHog telemetry is on by default. source |
| OpenMausBot B Supamaus Software Private Limited | Engines can point at any OpenAI-compatible endpoint per the README, but usage analytics are on by default. source |
| Qwen Code BB Qwen team, Alibaba Group (no legal entity is named in the repository or the docs) | `model.baseUrl` takes an OpenAI-compatible server and acc-25 ran Qwen3.6 35B locally, but `privacy.usageStatisticsEnabled` defaults on and must be set false. source |
| Mirror CLI C Reflection AI | `--api openai-chat-completions` with `--base-url` or `OPENROUTER_BASE_URL` reaches a local server, but analytics go to Statsig by default until turned off in `/settings` or `config.json`. source |
| Unstoppable E Unstoppable Domains, Inc. | The support index says Ollama can run models on your own computer, but the page was not read and the app's accounts and credits still sign in. source |
| Vibe-Trading C HKUDS | Ollama is supported, but market data pulls leave the machine by design and the CLI's update command calls PyPI. source |
Couldn't check 9
The docs were closed to us, or silent. These carry no mark either way.
| Listing | Why |
|---|---|
| Antigravity CLI C Google LLC | The models page lists a Local models section in its navigation, but the rendered page gave only the hosted model list and the section was not read. |
| DeepSeek Harness (dsh) D DeepSeek (the LICENSE names DeepSeek, and no legal entity is named in the repository or the docs) | The pages read name only the native DeepSeek adapter; whether an OpenAI-compatible local endpoint can be configured was not found. |
| dsh-superagent (DeepSeek) E DeepSeek (the LICENSE names the DeepSeek Harness Team; DeepSeek Harness's terms name Hangzhou DeepSeek Artificial Intelligence Co., Ltd.) | The model comes from the DSH profile; whether a local endpoint works was not established for DSH either. |
| Droid CLI C The San Francisco AI Factory, Inc. | The CLI reference points to a Custom Models (BYOK) page for other models, which was not read, so local endpoint support is unknown. |
| HarnessRouter D Lumentree Corporation | Model calls are at the provider's price or on your own keys; whether the self-hosted Community Edition reaches a local model was not read. |
| Paperclip C Paperclip Labs, Inc. | Custom model provider connectors are listed in the docs index but the page was not read; CLI adapters inherit the harness's model. |
| Prime Agent C Prime Intellect, Inc. | `models.json` takes provider overrides, but no local or OpenAI-compatible endpoint setup was found in the pages read. |
| Qoder CLI C BRIGHT ZENITH PRIVATE LIMITED | docs.qoder.com answered 502 from the fetch proxy on three attempts and a DNS failure through WebFetch, so no page was read. |
| Sculptor C Imbue, Inc. | The Pi harness lists providers from its own backend; whether a local endpoint is among them is not in the pages read. |
Doesn't do this job 23
Listings in the category that do something else, with the reason.
| Listing | Why |
|---|---|
| Amp C Amp Frontier Corporation | The settings reference has no local or OpenAI-compatible endpoint setting; models are Amp-served or the account's provider subscriptions, and every thread goes through Amp's servers. source |
| Auggie CLI D Augment Computing, Inc. | --model picks from Augment's hosted model list; no local or OpenAI-compatible endpoint option appears in the reference. source |
| Claude Code C Anthropic, PBC | The docs name Anthropic's API, Bedrock, Google Cloud's Agent Platform, Microsoft Foundry and Anthropic-compatible gateways through ANTHROPIC_BASE_URL; no local OpenAI-compatible server or non-Claude model is supported. source |
| CLI Manager BB solhun (Jeong Kyeonghun) | CLI Manager runs no model loop; the model belongs to the child harness. source |
| Conductor E Conductor | Conductor runs other harnesses; the model is theirs. source |
| Cursor CLI E Anysphere, Inc. | --model picks from Cursor's hosted list; no local endpoint option appears in the parameters. source |
| Devin C Cognition AI, Inc. | Hosted agent on Cognition's models and VMs. source |
| Emdash C General Action, Inc. | Emdash runs no model loop; the model belongs to the child agent. source |
| Gemini CLI B Google LLC | Gemini models through a Gemini API key, Vertex AI or Code Assist only. source |
| Harness B Autonomous, Inc. | Harness runs no model loop; local models belong to the agents it hosts. source |
| Harness² E Google LLC | Models are configured on Vertex AI or another cloud provider; the local demo uses deterministic editors with no model. source |
| Jules D Google LLC | Gemini models in Google's VMs only, and read-only since 11 November 2026. source |
| Kiro CLI B Amazon Web Services, Inc. | Models are Kiro's hosted list selected with `--model`; no custom endpoint or local provider setting is documented. source |
| Muse Code C Meta Platforms, Inc. | A Meta credential is required before the model can be called; no local or OpenAI-compatible endpoint is documented. source |
| OpenAI Agents API BB OpenAI OpCo, LLC | Models are OpenAI's; the loop runs on OpenAI's service. source |
| Orca C Lovecast Inc. | Orca runs other CLI agents; the model choice belongs to them. source |
| Parallax E Conifer Solutions, Inc. | Reviewers are models from other labs picked by Conifer's router. source |
| Paseo B Mohamed Boudra | Paseo runs provider CLIs; model choice is theirs. It sends no telemetry of its own. source |
| Rovo Dev CLI E Atlassian Pty Ltd | Models are Atlassian-hosted with credit multipliers; no custom endpoint setting. source |
| T3 Code C T3 Tools Inc. | T3 Code drives provider CLIs; model choice is theirs. source |
| Traycer C Traycer AI | Traycer drives provider CLIs or its own inference. source |
| Verdent E Verdent AI, Inc. | BYOK and BYOA take provider keys and CLIs; no local endpoint is documented. source |
| Warp (Warp Agent CLI and the Oz Agent API) C Denver Technologies, Inc. (d/b/a Warp) | Bring your own API key routes through Warp's server-side harness; no local endpoint. source |
What stops agents finishing
- chat template mismatch so tool calls are printed, not run (acc-23)
- model unloads between calls and the MCP transport closes (acc-18)
- 1 to 3 tokens a second on small hardware, and the harness falls back to a paid provider silently (acc-29)
- the harness's own telemetry or update ping still leaves the machine
Around it
Before: model-serving.start-server. After: agent-harnesses.pair-in-terminal.
Where this comes from
Weight 8 of 100 in Agent harnesses: 5 of 33 accounts (acc-18, acc-23, acc-24, acc-25, acc-29)
The same as data: /api/v1/use-cases/agent-harnesses.local-model.json, or the MCP tool get_use_case with id agent-harnesses.local-model. Other jobs in this category: /api/v1/niches?category=agent-harnesses.
For companies
Do agents find, use and choose your tools?
An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.