diff --git a/.SYNC_INFO.md b/.SYNC_INFO.md index 4a6c629..43fbcaa 100644 --- a/.SYNC_INFO.md +++ b/.SYNC_INFO.md @@ -4,8 +4,8 @@ This is a mirror of the Ollama repository. **Synced from:** https://github.com/ollama/ollama.git **Branch:** main -**Commit:** 8f45236d09332949aa91774dc9eb46caf2abbbc1 -**Sync Date:** 2026-03-12 +**Commit:** 9330bb912079ed1ba3c384cc762728700c9e3691 +**Sync Date:** 2026-04-12 **Content:** Paths: docs --- diff --git a/docs/api/openai-compatibility.mdx b/docs/api/openai-compatibility.mdx index 4c37d81..ddf93d2 100644 --- a/docs/api/openai-compatibility.mdx +++ b/docs/api/openai-compatibility.mdx @@ -184,6 +184,7 @@ curl -X POST http://localhost:11434/v1/chat/completions \ - [x] Reproducible outputs - [x] Vision - [x] Tools +- [x] Reasoning/thinking control (for thinking models) - [ ] Logprobs #### Supported request fields @@ -207,6 +208,9 @@ curl -X POST http://localhost:11434/v1/chat/completions \ - [x] `top_p` - [x] `max_tokens` - [x] `tools` +- [x] `reasoning_effort` (`"high"`, `"medium"`, `"low"`, `"none"`) +- [x] `reasoning` + - [x] `effort` (`"high"`, `"medium"`, `"low"`, `"none"`) - [ ] `tool_choice` - [ ] `logit_bias` - [ ] `user` diff --git a/docs/cli.mdx b/docs/cli.mdx index ca03a52..5ff2995 100644 --- a/docs/cli.mdx +++ b/docs/cli.mdx @@ -21,6 +21,7 @@ Configure and launch external applications to use Ollama models. This provides a - **OpenCode** - Open-source coding assistant - **Claude Code** - Anthropic's agentic coding tool - **Codex** - OpenAI's coding assistant +- **VS Code** - Microsoft's IDE with built-in AI chat - **Droid** - Factory's AI coding agent #### Examples diff --git a/docs/docs.json b/docs/docs.json index 3f8b5c1..3b2e651 100644 --- a/docs/docs.json +++ b/docs/docs.json @@ -110,7 +110,8 @@ "group": "Assistants", "expanded": true, "pages": [ - "/integrations/openclaw" + "/integrations/openclaw", + "/integrations/hermes" ] }, { @@ -127,6 +128,7 @@ }, { "group": "IDEs & Editors", + "expanded": true, "pages": [ "/integrations/cline", "/integrations/jetbrains", @@ -160,6 +162,12 @@ "group": "More information", "pages": [ "/cli", + { + "group": "Assistant Sandboxing", + "pages": [ + "/integrations/nemoclaw" + ] + }, "/modelfile", "/context-length", "/linux", diff --git a/docs/gpu.mdx b/docs/gpu.mdx index e129cdc..e1009e3 100644 --- a/docs/gpu.mdx +++ b/docs/gpu.mdx @@ -61,6 +61,10 @@ Ollama supports the following AMD GPUs via the ROCm library: ### Linux Support +Ollama requires the AMD ROCm v7 driver on Linux. You can install or upgrade +using the `amdgpu-install` utility from +[AMD's ROCm documentation](https://rocm.docs.amd.com/projects/install-on-linux/en/latest/). + | Family | Cards and accelerators | | -------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------- | | AMD Radeon RX | `9070 XT` `9070 GRE` `9070` `9060 XT` `9060 XT LP` `9060` `7900 XTX` `7900 XT` `7900 GRE` `7800 XT` `7700 XT` `7700` `7600 XT` `7600` `6950 XT` `6900 XTX` `6900XT` `6800 XT` `6800` `5700 XT` `5700` `5600 XT` `5500 XT` | diff --git a/docs/images/local.png b/docs/images/local.png new file mode 100644 index 0000000..69f7940 Binary files /dev/null and b/docs/images/local.png differ diff --git a/docs/images/vscode-add-ollama.png b/docs/images/vscode-add-ollama.png new file mode 100644 index 0000000..73fe417 Binary files /dev/null and b/docs/images/vscode-add-ollama.png differ diff --git a/docs/images/vscode-model-options.png b/docs/images/vscode-model-options.png deleted file mode 100644 index b1cca5d..0000000 Binary files a/docs/images/vscode-model-options.png and /dev/null differ diff --git a/docs/images/vscode-models.png b/docs/images/vscode-models.png deleted file mode 100644 index af250ea..0000000 Binary files a/docs/images/vscode-models.png and /dev/null differ diff --git a/docs/images/vscode-other-models.png b/docs/images/vscode-other-models.png new file mode 100644 index 0000000..9b2b69a Binary files /dev/null and b/docs/images/vscode-other-models.png differ diff --git a/docs/images/vscode-unhide.png b/docs/images/vscode-unhide.png new file mode 100644 index 0000000..9f71fbd Binary files /dev/null and b/docs/images/vscode-unhide.png differ diff --git a/docs/images/vscode.png b/docs/images/vscode.png new file mode 100644 index 0000000..fa2ef23 Binary files /dev/null and b/docs/images/vscode.png differ diff --git a/docs/integrations/claude-code.mdx b/docs/integrations/claude-code.mdx index 5bae29e..3e287b5 100644 --- a/docs/integrations/claude-code.mdx +++ b/docs/integrations/claude-code.mdx @@ -41,13 +41,27 @@ ollama launch claude --model kimi-k2.5:cloud - `kimi-k2.5:cloud` - `glm-5:cloud` -- `minimax-m2.5:cloud` +- `minimax-m2.7:cloud` - `qwen3.5:cloud` - `glm-4.7-flash` - `qwen3.5` Cloud models are also available at [ollama.com/search?c=cloud](https://ollama.com/search?c=cloud). +## Non-interactive (headless) mode + +Run Claude Code without interaction for use in Docker, CI/CD, or scripts: + +```shell +ollama launch claude --model kimi-k2.5:cloud --yes -- -p "how does this repository work?" +``` + +The `--yes` flag auto-pulls the model, skips selectors, and requires `--model` to be specified. Arguments after `--` are passed directly to Claude Code. + +## Web search + +Claude Code can search the web through Ollama's web search API. See the [web search documentation](/capabilities/web-search) for setup and usage. + ## Scheduled Tasks with `/loop` The `/loop` command runs a prompt or slash command on a recurring schedule inside Claude Code. This is useful for automating repetitive tasks like checking PRs, running research, or setting reminders. @@ -82,6 +96,18 @@ The `/loop` command runs a prompt or slash command on a recurring schedule insid /loop 1h Remind me to review the deploy status ``` +## Telegram + +Chat with Claude Code from Telegram by connecting a bot to your session. Install the [Telegram plugin](https://github.com/anthropics/claude-plugins-official), create a bot via [@BotFather](https://t.me/BotFather), then launch with the channel flag: + +```shell +ollama launch claude -- --channels plugin:telegram@claude-plugins-official +``` + +Claude Code will prompt for permission on most actions. To allow the bot to work autonomously, configure [permission rules](https://code.claude.com/docs/en/permissions) or pass `--dangerously-skip-permissions` in isolated environments. + +See the [plugin README](https://github.com/anthropics/claude-plugins-official/tree/main/external_plugins/telegram) for full setup instructions including pairing and access control. + ## Manual setup Claude Code connects to Ollama using the Anthropic-compatible API. diff --git a/docs/integrations/codex.mdx b/docs/integrations/codex.mdx index 7a79d39..1888809 100644 --- a/docs/integrations/codex.mdx +++ b/docs/integrations/codex.mdx @@ -35,36 +35,39 @@ To use `codex` with Ollama, use the `--oss` flag: codex --oss ``` -### Changing Models - -By default, codex will use the local `gpt-oss:20b` model. However, you can specify a different model with the `-m` flag: +To use a specific model, pass the `-m` flag: ``` codex --oss -m gpt-oss:120b ``` -### Cloud Models +To use a cloud model: ``` codex --oss -m gpt-oss:120b-cloud ``` +### Profile-based setup -## Connecting to ollama.com - - -Create an [API key](https://ollama.com/settings/keys) from ollama.com and export it as `OLLAMA_API_KEY`. - -To use ollama.com directly, edit your `~/.codex/config.toml` file to point to ollama.com. +For a persistent configuration, add an Ollama provider and profiles to `~/.codex/config.toml`: ```toml -model = "gpt-oss:120b" -model_provider = "ollama" - -[model_providers.ollama] +[model_providers.ollama-launch] name = "Ollama" -base_url = "https://ollama.com/v1" -env_key = "OLLAMA_API_KEY" +base_url = "http://localhost:11434/v1" + +[profiles.ollama-launch] +model = "gpt-oss:120b" +model_provider = "ollama-launch" + +[profiles.ollama-cloud] +model = "gpt-oss:120b-cloud" +model_provider = "ollama-launch" ``` -Run `codex` in a new terminal to load the new settings. +Then run: + +``` +codex --profile ollama-launch +codex --profile ollama-cloud +``` diff --git a/docs/integrations/hermes.mdx b/docs/integrations/hermes.mdx new file mode 100644 index 0000000..590f8ec --- /dev/null +++ b/docs/integrations/hermes.mdx @@ -0,0 +1,111 @@ +--- +title: Hermes Agent +--- + +Hermes Agent is a self-improving AI agent built by Nous Research. It features automatic skill creation, cross-session memory, and connects messaging platforms (Telegram, Discord, Slack, WhatsApp, Signal, Email) to models through a unified gateway. + +## Quick start + +### Pull a model + +Before running the setup wizard, make sure you have a model available. Hermes will auto-detect models downloaded through Ollama. + +```bash +ollama pull kimi-k2.5:cloud +``` + +See [Recommended models](#recommended-models) for more options. + +### Install + +```bash +curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash +``` + +### Set up + +After installation, Hermes launches the setup wizard automatically. Choose **Quick setup**: + +``` +How would you like to set up Hermes? + + → Quick setup — provider, model & messaging (recommended) + Full setup — configure everything +``` + +### Connect to Ollama + +1. Select **More providers...** +2. Select **Custom endpoint (enter URL manually)** +3. Set the API base URL to the Ollama OpenAI-compatible endpoint: + + ``` + API base URL [e.g. https://api.example.com/v1]: http://127.0.0.1:11434/v1 + ``` + +4. Leave the API key blank (not required for local Ollama): + + ``` + API key [optional]: + ``` + +5. Hermes auto-detects downloaded models, confirm the one you want: + + ``` + Verified endpoint via http://127.0.0.1:11434/v1/models (1 model(s) visible) + Detected model: kimi-k2.5:cloud + Use this model? [Y/n]: + ``` + +6. Leave context length blank to auto-detect: + + ``` + Context length in tokens [leave blank for auto-detect]: + ``` + +### Connect messaging + +Optionally connect a messaging platform during setup: + +``` +Connect a messaging platform? (Telegram, Discord, etc.) + + → Set up messaging now (recommended) + Skip — set up later with 'hermes setup gateway' +``` + +### Launch + +``` +Launch hermes chat now? [Y/n]: Y +``` + +## Recommended models + +**Cloud models**: + +- `kimi-k2.5:cloud` — Multimodal reasoning with subagents +- `qwen3.5:cloud` — Reasoning, coding, and agentic tool use with vision +- `glm-5.1:cloud` — Reasoning and code generation +- `minimax-m2.7:cloud` — Fast, efficient coding and real-world productivity + +**Local models:** + +- `gemma4` — Reasoning and code generation locally (~16 GB VRAM) +- `qwen3.5` — Reasoning, coding, and visual understanding locally (~11 GB VRAM) + +More models at [ollama.com/search](https://ollama.com/models). + +## Configure later + +Re-run the setup wizard at any time: + +```bash +hermes setup +``` + +To configure just messaging: + +```bash +hermes setup gateway +``` diff --git a/docs/integrations/index.mdx b/docs/integrations/index.mdx index 5ae2fe6..2703fc0 100644 --- a/docs/integrations/index.mdx +++ b/docs/integrations/index.mdx @@ -20,6 +20,7 @@ Coding assistants that can read, modify, and execute code in your projects. AI assistants that help with everyday tasks. - [OpenClaw](/integrations/openclaw) +- [Hermes Agent](/integrations/hermes) ## IDEs & Editors diff --git a/docs/integrations/nemoclaw.mdx b/docs/integrations/nemoclaw.mdx new file mode 100644 index 0000000..0aee01a --- /dev/null +++ b/docs/integrations/nemoclaw.mdx @@ -0,0 +1,67 @@ +--- +title: NemoClaw +--- + +NemoClaw is NVIDIA's open source security stack for [OpenClaw](/integrations/openclaw). It wraps OpenClaw with the NVIDIA OpenShell runtime to provide kernel-level sandboxing, network policy controls, and audit trails for AI agents. + +## Quick start + +Pull a model: + +```bash +ollama pull nemotron-3-nano:30b +``` + +Run the installer: + +```bash +curl -fsSL https://www.nvidia.com/nemoclaw.sh | \ + NEMOCLAW_NON_INTERACTIVE=1 \ + NEMOCLAW_PROVIDER=ollama \ + NEMOCLAW_MODEL=nemotron-3-nano:30b \ + bash +``` + +Connect to your sandbox: + +```bash +nemoclaw my-assistant connect +``` + +Open the TUI: + +```bash +openclaw tui +``` + +Ollama support in NemoClaw is still experimental. + +## Platform support + +| Platform | Runtime | Status | +|----------|---------|--------| +| Linux (Ubuntu 22.04+) | Docker | Primary | +| macOS (Apple Silicon) | Colima or Docker Desktop | Supported | +| Windows | WSL2 with Docker Desktop | Supported | + +CMD and PowerShell are not supported on Windows — WSL2 is required. + +Ollama must be installed and running before the installer runs. When running inside WSL2 or a container, ensure Ollama is reachable from the sandbox (e.g. `OLLAMA_HOST=0.0.0.0`). + +## System requirements + +- CPU: 4 vCPU minimum +- RAM: 8 GB minimum (16 GB recommended) +- Disk: 20 GB free (40 GB recommended for local models) +- Node.js 20+ and npm 10+ +- Container runtime (Docker preferred) + +## Recommended models + +- `nemotron-3-super:cloud` — Strong reasoning and coding +- `qwen3.5:cloud` — 397B; reasoning and code generation +- `nemotron-3-nano:30b` — Recommended local model; fits in 24 GB VRAM +- `qwen3.5:27b` — Fast local reasoning (~18 GB VRAM) +- `glm-4.7-flash` — Reasoning and code generation (~25 GB VRAM) + +More models at [ollama.com/search](https://ollama.com/search). diff --git a/docs/integrations/openclaw.mdx b/docs/integrations/openclaw.mdx index 957f1c2..10df4a1 100644 --- a/docs/integrations/openclaw.mdx +++ b/docs/integrations/openclaw.mdx @@ -15,13 +15,29 @@ Ollama handles everything automatically: 1. **Install** — If OpenClaw isn't installed, Ollama prompts to install it via npm 2. **Security** — On the first launch, a security notice explains the risks of tool access 3. **Model** — Pick a model from the selector (local or cloud) -4. **Onboarding** — Ollama configures the provider, installs the gateway daemon, and sets your model as the primary +4. **Onboarding** — Ollama configures the provider, installs the gateway daemon, sets your model as the primary, and installs the web search and fetch plugin 5. **Gateway** — Starts in the background and opens the OpenClaw TUI OpenClaw requires a larger context window. It is recommended to use a context window of at least 64k tokens if using local models. See [Context length](/context-length) for more information. Previously known as Clawdbot. `ollama launch clawdbot` still works as an alias. +## Web search and fetch + +OpenClaw ships with a web search and fetch plugin that gives local or cloud models the ability to search the web and extract readable page content. + +```bash +ollama launch openclaw +``` + +Web search and fetch is enabled automatically when launching OpenClaw through Ollama. To install the plugin directly: + +```bash +openclaw plugins install @ollama/openclaw-web-search +``` + +Web search for local models requires `ollama signin`. + ## Configure without launching To change the model without starting the gateway and TUI: @@ -43,15 +59,27 @@ If the gateway is already running, it restarts automatically to pick up the new **Cloud models**: - `kimi-k2.5:cloud` — Multimodal reasoning with subagents -- `minimax-m2.5:cloud` — Fast, efficient coding and real-world productivity -- `glm-5:cloud` — Reasoning and code generation +- `qwen3.5:cloud` — Reasoning, coding, and agentic tool use with vision +- `glm-5.1:cloud` — Reasoning and code generation +- `minimax-m2.7:cloud` — Fast, efficient coding and real-world productivity **Local models:** -- `glm-4.7-flash` — Reasoning and code generation locally (~25 GB VRAM) +- `gemma4` — Reasoning and code generation locally (~16 GB VRAM) +- `qwen3.5` — Reasoning, coding, and visual understanding locally (~11 GB VRAM) More models at [ollama.com/search](https://ollama.com/search?c=cloud). +## Non-interactive (headless) mode + +Run OpenClaw without interaction for use in Docker, CI/CD, or scripts: + +```bash +ollama launch openclaw --model kimi-k2.5:cloud --yes +``` + +The `--yes` flag auto-pulls the model, skips selectors, and requires `--model` to be specified. + ## Connect messaging apps ```bash diff --git a/docs/integrations/pi.mdx b/docs/integrations/pi.mdx index fd2dadb..e7e79b8 100644 --- a/docs/integrations/pi.mdx +++ b/docs/integrations/pi.mdx @@ -2,7 +2,7 @@ title: Pi --- -Pi is a minimal AI agent toolkit with plugin support. +Pi is a minimal and extensible coding agent. ## Install @@ -20,13 +20,65 @@ npm install -g @mariozechner/pi-coding-agent ollama launch pi ``` +This installs Pi, configures Ollama as a provider including web tools, and drops you into an interactive session. + To configure without launching: ```shell ollama launch pi --config ``` -### Manual setup +### Run directly with a model + +```shell +ollama launch pi --model qwen3.5:cloud +``` + +Cloud models are also available at [ollama.com](https://ollama.com/search?c=cloud). + +## Extensions + +Pi ships with four core tools: `read`, `write`, `edit`, and `bash`. All other capabilities are added through its extension system. + +On-demand capability packages invoked via `/skill:name` commands. + +Install from npm or git: + +```bash +pi install npm:@foo/some-tools +pi install git:github.com/user/repo@v1 +``` + +See all packages at [pi.dev](https://pi.dev/packages) + +### Web search + +Pi can use web search and fetch tools via the `@ollama/pi-web-search` package. + +When launching Pi through Ollama, package install/update is managed automatically. +To install manually: + +```bash +pi install npm:@ollama/pi-web-search +``` + +### Autoresearch with `pi-autoresearch` + +[pi-autoresearch](https://github.com/davebcn87/pi-autoresearch) brings autonomous experiment loops to Pi. Inspired by Karpathy's autoresearch, it turns any measurable metric into an optimization target: test speed, bundle size, build time, model training loss, Lighthouse scores. + +```bash +pi install https://github.com/davebcn87/pi-autoresearch +``` + +Tell Pi what to optimize. It runs experiments, benchmarks each one, keeps improvements, reverts regressions, and repeats — all autonomously. A built-in dashboard tracks every run with confidence scoring to distinguish real gains from benchmark noise. + +```bash +/autoresearch optimize unit test runtime +``` + +Each kept experiment is automatically committed. Each failed one is reverted. When you're done, Pi can group improvements into independent branches for clean review and merge. + +## Manual setup Add a configuration block to `~/.pi/agent/models.json`: diff --git a/docs/integrations/vscode.mdx b/docs/integrations/vscode.mdx index c04059b..63e58d7 100644 --- a/docs/integrations/vscode.mdx +++ b/docs/integrations/vscode.mdx @@ -2,33 +2,84 @@ title: VS Code --- -## Install +VS Code includes built-in AI chat through GitHub Copilot Chat. Ollama models can be used directly in the Copilot Chat model picker. -Install [VS Code](https://code.visualstudio.com/download). -## Usage with Ollama +![VS Code with Ollama](/images/vscode.png) -1. Open Copilot side bar found in top right window + +## Prerequisites + +- Ollama v0.18.3+ +- [VS Code 1.113+](https://code.visualstudio.com/download) +- [GitHub Copilot Chat extension 0.41.0+](https://marketplace.visualstudio.com/items?itemName=GitHub.copilot-chat) + + VS Code requires you to be logged in to use its model selector, even for custom models. This doesn't require a paid GitHub Copilot account; GitHub Copilot Free will enable model selection for custom models. + +## Quick setup + +```shell +ollama launch vscode +``` + +Recommended models will be shown after running the command. See the latest models at [ollama.com](https://ollama.com/search?c=tools). + +Make sure **Local** is selected at the bottom of the Copilot Chat panel to use your Ollama models. +
+ Ollama Local Models +
+ + +## Run directly with a model + +```shell +ollama launch vscode --model qwen3.5:cloud +``` +Cloud models are also available at [ollama.com](https://ollama.com/search?c=cloud). + +## Manual setup + +To configure Ollama manually without `ollama launch`: + +1. Open the **Copilot Chat** side bar from the top right corner
VS Code chat Sidebar
-2. Select the model dropdown > **Manage models** +2. Click the **settings gear icon** () to bring up the Language Models window
VS Code model picker
-3. Enter **Ollama** under **Provider Dropdown** and select desired models (e.g `qwen3, qwen3-coder:480b-cloud`) +3. Click **Add Models** and select **Ollama** to load all your Ollama models into VS Code
VS Code model options dropdown +
+ +4. Click the **Unhide** button in the model picker to show your Ollama models +
+ VS Code unhide models button
diff --git a/docs/troubleshooting.mdx b/docs/troubleshooting.mdx index 9083dd8..72a34f2 100644 --- a/docs/troubleshooting.mdx +++ b/docs/troubleshooting.mdx @@ -114,6 +114,25 @@ If you are experiencing problems getting Ollama to correctly discover or use you - `OLLAMA_DEBUG=1` During GPU discovery additional information will be reported - Check dmesg for any errors from amdgpu or kfd drivers `sudo dmesg | grep -i amdgpu` and `sudo dmesg | grep -i kfd` +### AMD Driver Version Mismatch + +If your AMD GPU is not detected on Linux and the server logs contain messages like: + +``` +msg="failure during GPU discovery" ... error="failed to finish discovery before timeout" +msg="bootstrap discovery took" duration=30s ... +``` + +This typically means the system's AMD GPU driver is too old. Ollama bundles +ROCm 7 linux libraries which require a compatible ROCm 7 kernel driver. If the +system is running an older driver (ROCm 6.x or earlier), GPU initialization +will hang during device discovery and eventually time out, causing Ollama to +fall back to CPU. + +To resolve this, upgrade to the ROCm v7 driver using the `amdgpu-install` +utility from [AMD's ROCm documentation](https://rocm.docs.amd.com/projects/install-on-linux/en/latest/). +After upgrading, reboot and restart Ollama. + ## Multiple AMD GPUs If you experience gibberish responses when models load across multiple AMD GPUs on Linux, see the following guide. diff --git a/docs/windows.mdx b/docs/windows.mdx index 37fd197..555efb9 100644 --- a/docs/windows.mdx +++ b/docs/windows.mdx @@ -80,9 +80,13 @@ help you keep up to date. If you'd like to install or integrate Ollama as a service, a standalone `ollama-windows-amd64.zip` zip file is available containing only the Ollama CLI -and GPU library dependencies for Nvidia. If you have an AMD GPU, also download -and extract the additional ROCm package `ollama-windows-amd64-rocm.zip` into the -same directory. This allows for embedding Ollama in existing applications, or +and GPU library dependencies for Nvidia. Depending on your hardware, you may also +need to download and extract additional packages into the same directory: + +- **AMD GPU**: `ollama-windows-amd64-rocm.zip` +- **MLX (CUDA)**: `ollama-windows-amd64-mlx.zip` + +This allows for embedding Ollama in existing applications, or running it as a system service via `ollama serve` with tools such as [NSSM](https://nssm.cc/).