TaewoooPark/Motifcode

Última actividad de origen registrada: 26 de septiembre de 2026 a las 12:01

Catálogo de SkillsMP actualizado: 2 de noviembre de 2026 a las 18:02

skills recopiladas: 6

Estrellas en GitHub: 79
Forks en GitHub: 16

Instalar con un asistente de IA

Copia este prompt en el asistente de IA que estés usando.

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/TaewoooPark/Motifcode.

README del repositorio

Archivo de origen del README: README.md

Leer el README original

Mostrar README completo

<img src="docs/logo.svg" alt="motifcode" width="912"> A coding agent harness built for one model: Motif-3. English  ·  <a href="README.ko.md">한국어</a> <img src="https://img.shields.io/npm/v/motifcode?style=flat-square&labelColor=000000&color=333333" alt="npm"> <img src="https://img.shields.io/github/last-commit/TaewoooPark/Motifcode?style=flat-square&labelColor=000000&color=333333" alt="Last commit"> <img src="https://img.shields.io/github/actions/workflow/status/TaewoooPark/Motifcode/ci.yml?branch=main&style=flat-square&labelColor=000000&color=333333" alt="CI"> <img src="https://img.shields.io/badge/license-Apache--2.0-000000?style=flat-square&labelColor=000000&color=333333" alt="Apache-2.0">   <img src="https://img.shields.io/badge/TypeScript-000000?style=flat-square&logo=typescript&logoColor=white&labelColor=000000" alt="TypeScript"> <img src="https://img.shields.io/badge/Python-000000?style=flat-square&logo=python&logoColor=white&labelColor=000000" alt="Python"> <img src="https://img.shields.io/badge/Vitest-000000?style=flat-square&logo=vitest&logoColor=white&labelColor=000000" alt="Vitest">   <img src="https://img.shields.io/badge/Motif--3-000000?style=flat-square&labelColor=000000&color=000000" alt="Motif-3"> <img src="https://img.shields.io/badge/314B--A13B-000000?style=flat-square&labelColor=000000&color=000000" alt="314B-A13B"> <img src="https://img.shields.io/badge/256K%20context-000000?style=flat-square&labelColor=000000&color=000000" alt="256K context"> <img src="https://img.shields.io/badge/alpha-000000?style=flat-square&labelColor=000000&color=000000" alt="alpha"> <a href="https://discord.gg/5d99wCtzc"><img src="https://img.shields.io/badge/Join_OpenLab-Discord-5865F2?style=for-the-badge&logo=discord&logoColor=white&labelColor=000000" alt="Join OpenLab on Discord"></a> > **Choose your provider.** First launch offers [Infron](https://infron.ai) or > [Morphfactory (BETA)](https://cbt.morphfactory.io/console?view=keys). > Switch later with `/provider` or from `/config`; each provider keeps its own API key. > **Not an official Motif project.** Motifcode is an independent open-source project. > It is not certified, endorsed, sponsored or maintained by Motif Technologies or by > Infron. *Motif* and *Motif-3* are their names; this repository is only a client of the model. Motifcode is a terminal coding agent in the shape of Claude Code — a transcript above, a bordered prompt below, `/` commands, `@` mentions, a permission prompt, a `.motif/` directory behind it — whose tool set, prompt layout, parser and failure handling are **consequences of things that are specifically true about [Motif-3](https://huggingface.co/Motif-Technologies/Motif-3)**, most of them measured rather than assumed. It is not a general harness pointed at a different base URL. <img src="docs/screen-large.jpg" alt="motif in a wide terminal" width="912"> --- ## Why this exists On 18 August 2026 Korea's Ministry of Science and ICT announced the second-stage result of its **Independent AI Foundation Model** programme (독자 AI 파운데이션 모델, the national sovereign-model project). Four teams were evaluated; LG AI Research, SK Telecom and Upstage went on to the next round, and **Motif Technologies was eliminated** — with the highest benchmark score of the four. The vice minister's explanation was that the technology was excellent but that the model *"received a somewhat lower evaluation than the other companies on usability and applicability"* (사용성·활용성). A week earlier Motif-3 had been released as open weights, scoring 47 on the Artificial Analysis Intelligence Index — first among Korean models. ([THE ELEC](https://www.thelec.kr/news/articleView.html?idxno=61033), [Biz Hankook](https://bizhankook.com/articles/motif-eliminated-doks-round-3-change.html), [HelloT](https://www.hellot.net/news/article.html?no=114379); the score has since been revised to 34 following changes to the scoring system) *Usability*, for a coding model, is mostly not a property of the weights. It is whether the model's tool calls parse; whether the prompt is laid out the way its own chat template expects; whether one malformed turn is repaired or ends the session; whether the tools it is given are the ones it scored with; and whether the terminal in front of the person behaves like the tools they already use. Every one of those is a property of the harness — and a harness can be written by anyone. **Motifcode was built to prove that the usability an open-weight model was marked down on can be raised far enough with open source.** The harness is written for this one model, measured against it, and given an interactive session checked feature by feature against Claude Code's. --- ## What it looks like <table> <tr> <td width="50%" align="center" valign="top"> <img src="docs/screen-large.jpg" alt="motif in a wide terminal" width="100%"> Wide window. The hero, the welcome card and the prompt. </td> <td width="50%" align="center" valign="top"> <img src="docs/screen-small.jpg" alt="motif in a narrow terminal" width="100%"> Narrow window. The hero picks the size that fits; the session is the same. </td> </tr> <tr> <td width="50%" align="center" valign="top"> <img src="docs/screen-login.jpg" alt="the first run asks for the API key" width="100%"> First run. Choose a provider, then paste an API key to check and save once. </td> <td width="50%" align="center" valign="top"> <img src="docs/screen-skills.jpg" alt="the /skills list" width="100%"> <code>/skills</code>. The built-in skills, each of them also a command: <code>/commit fix the parser</code>. </td> </tr> </table> The hero fits the window; the welcome card says what to type; the first run asks for the key in place of the prompt. In a session, your line follows `>`, the model's prose and each tool call sit behind a `⏺`, results under a `⎿`, reasoning stays hidden unless you ask for it, and the status line shows the context used and how much of the prompt the server served from cache. --- ## Install and use Needs **Node 20.3+**. The package is one file with no runtime dependencies. ```bash cd your-project npx motifcode # first run: asks for your key, then offers to install the `motif` command ``` The first session lets you choose **Infron** or **Morphfactory (BETA)**, asks for your API key once, and saves it to `~/.motif/.env`. Because `npx` leaves no command behind, it then offers to run `npm install -g motifcode` for you; say yes and `motif` (or `motifcode`) opens the session from any folder from then on. `npm install -g motifcode` directly does the same without the question. | command | what it does | |---|---| | `motif` | open the interactive session in the current directory | | `motif --continue` | the same, with the latest conversation here loaded | | `motif "<task>"` | run one task and exit; `--interactive` stays in the session afterwards | | `motif -p "<question>"` | print only the final reply, for scripts and pipes | | `motif login` · `motif logout` | paste a key outside a session; remove the saved key | | `motif doctor` | probe the endpoint: auth, tool-call and reasoning parsers, prefix cache, channels | | `motif mcp add NAME -- COMMAND [ARGS...]` | register a local stdio MCP server | | `motif mcp presets [ID]` · `install ID` | browse built-in presets and register one offline; `--enable` opts in to startup | | `motif mcp add NAME --transport http URL` | register a Streamable HTTP MCP server; use `sse` for legacy SSE | | `motif mcp list` · `get NAME` · `doctor --connect` | inspect MCP configuration and check server connections | | `motif mcp enable NAME` · `disable NAME` · `remove NAME` | change saved MCP registrations | | `motif mcp connect NAME --login` · `login NAME` · `logout NAME` | check a connection, sign in through the provider, or clear local OAuth credentials | | `motif plugins list` · `inspect NAME` · `connect NAME` | discover built-in bundles and review or connect their services; also supports installed skill packages | | `motif mcp import codex\|claude PATH` | preview server settings from another client; `--write NEW_PATH` saves disabled entries | | `motif sessions` · `motif resume <file>` | list recorded sessions; resume an interrupted one | | `motif skills` · `agents` · `plugins` · `config` | what is loaded, and the effective settings with their sources | | `motif skills add` · `import` · `marketplace` | install skills from local/Git sources, Claude, Codex and marketplace packages | | `motif trust` | approve this repository's `.motif/settings.json` hooks | Flags: `--model`, `--endpoint`, `--env-file`, `--theme`, `--thinking`, `--verbose`, `--permissions ask|auto`, `--cwd`, `--channel`, `--max-turns`, `--max-output-tokens`, `--seed`, `--no-hero`. `motif --help` has the full list. [MCP servers](#mcp-servers) and [Skills](#skills) walk through the `mcp`, `skills` and `plugins` commands. If your terminal is configured to render East Asian Ambiguous characters as two columns, launch with `MOTIF_AMBIGUOUS_WIDTH=2 motif` to match its cursor and wrapping behavior. The default is one column. Set this in the shell environment; it is a terminal preference, not an API configuration value in `.env`. --- ## MCP servers MCP servers give Motif outside tools: library documentation, GitHub, a browser, your own local services. Motif connects to stdio, Streamable HTTP and legacy SSE servers. Every server sits behind the one `mcp` tool, so connecting a server never changes the model's tool list. Each server tool is still called by its own name against its own JSON Schema, and the arguments are checked before they are sent. Server tools follow the session's permissions, and a write whose outcome is unknown is never repeated on its own. ### Built-in presets Eight presets ship with Motif. Browsing them is offline, and registering one downloads, starts and signs in to nothing. | Preset | What it adds | Transport | What it needs | |---|---|---|---| | `context7` | Current library and framework documentation | HTTP | Nothing; an API key only raises account limits | | `github` | Repositories, issues, pull requests and workflows | HTTP | GitHub CLI (`gh`); Motif reuses the account `gh` saved | | `playwright` | Browser navigation and page inspection | stdio (`npx`) | Node/npm and Chrome; runs headless in an isolated profile | | `filesystem` | Filesystem tools inside one directory | stdio (`npx`) | An existing directory you choose explicitly | | `hugging-face` | Public model, dataset and repository information | HTTP | Nothing; a Hugging Face token for authenticated features | | `openai-docs` | OpenAI developer documentation | HTTP | Nothing | | `tauri` | Tauri app inspection (community server) | stdio (`npx`) | A running Tauri 2 app with its MCP bridge plugin | | `gmail` | Gmail (preview) | HTTP | Your own Google OAuth access token; no built-in sign-in | `npx` presets download their pinned package on the first connection. See [preset requirements](docs/mcp.md#built-in-server-presets) for the details. ### Add a server **In a session.** Type `/mcp`. The manager lists the registered servers and the presets you can add. Select a preset to see what it needs and where it will be saved, then register and connect it. Its tools are usable in the same session, with no restart. `/mcp list`, `/mcp connect NAME`, `/mcp disconnect NAME`, `/mcp reconnect NAME` and `/mcp login NAME` work straight from the prompt. **A preset from the shell.** ```bash motif mcp presets # the catalog, offline motif mcp presets playwright # one preset's requirements motif mcp install context7 --enable motif mcp install filesystem --root /absolute/project/path --enable motif mcp install github --enable && motif mcp login github ``` `install` saves the registration, disabled unless `--enable` is given. **Any other server.** Motif's options go before `--`, the server's own command after it. HTTP and SSE servers take a URL: ```bash motif mcp add local -- node /absolute/path/to/server.mjs motif mcp add local-api --env-ref TOKEN=SERVICE_TOKEN -- node /absolute/path/to/server.mjs motif mcp add docs --transport http https://developers.openai.com/mcp motif mcp add remote --transport http --header 'Authorization=Bearer ${SERVICE_TOKEN}' https://example.com/mcp motif mcp add legacy --transport sse --header-env X-Api-Key=SERVICE_TOKEN https://example.com/sse ``` Pass credentials as environment references (`--env-ref`, `--header-env`, `${VAR}`) rather than values; private headers require them. Registrations are saved in `~/.motif/mcp.json`, which can also be [edited by hand](docs/mcp.md#configuration-and-trust). **From Codex or Claude.** ```bash motif mcp import codex ~/.codex/config.toml motif mcp import claude /path/to/claude-config.json --write ./mcp.imported.json ``` Import is a preview until `--write` names a new file. Imported entries stay disabled for review, and inline secrets are not copied. **By asking.** Paste the server's repository or URL with a clear request, and the built-in `mcp-setup` skill takes over: > Connect this MCP to Motifcode and check it: https://github.com/TaewoooPark/Trendchaser-mcp It reads the server's installation instructions, registers it and checks the connection under your usual permissions. `/mcp-setup <URL>` runs it explicitly. ### Sign in and check ```bash motif mcp list # registrations and presets, offline motif mcp doctor --connect # start enabled servers, list their tools, close them motif mcp connect NAME --login # connect, signing in through the browser if needed motif mcp login NAME --no-browser # print the sign-in URL instead, for SSH or headless machines ``` Servers that use standard MCP OAuth sign in through the browser. Motif opens the provider's page, receives the callback on a loopback port and keeps the tokens in private files under `~/.motif/auth`, never in `mcp.json` or in the model's context. In a session, a server that needs sign-in offers it, and the panel also shows the URL in case no browser can open. The GitHub preset reuses GitHub CLI's saved account instead: Motif stores only a delegation grant, `gh` keeps the token, and access survives restarts. `motif mcp logout NAME` removes Motif's credentials without signing you out of the provider or of `gh`. `~/.motif/mcp.json` is trusted. Project files are never picked up automatically: review one, then pass `--mcp-config FILE` together with the SHA-256 it prints to `--trust-mcp`. Servers added in `/mcp` connect at once; edits made from another terminal need a relaunch. The [MCP guide](docs/mcp.md) covers tool allowlists, timeouts, form and URL approvals and the full support matrix. --- ## Skills A skill is a folder with a `SKILL.md` (YAML frontmatter with a `name` and a `description`, then the instructions) and any scripts, references and assets beside it. It is the Agent Skills format that Claude Code and Codex use, and Motif reads both clients' variants. Only a short index sits in the system prompt; a skill's full body loads when it is used. Motif ships 18 core skills and 6 more in five workflow bundles. Run one as `/<name> [input]` (`/commit fix the parser`), attach it with `@skill:name`, or let the model choose it through the `skill` tool. `/skills` lists what is loaded. ### Claude Code and Codex compatibility | In the source skill | In Motif | |---|---| | `SKILL.md` frontmatter, references, scripts, assets | Loaded with the skill's own directory as its base | | `$ARGUMENTS`, `$ARGUMENTS[N]`, `$N` | Filled from the words after the command; quoted words stay together | | `${CLAUDE_SKILL_DIR}`, `${CLAUDE_PLUGIN_ROOT}` | The skill's directory, and its package root when installed from a package | | Claude `disable-model-invocation`, `user-invocable` | Respected: user-only, or hidden from the user | | Codex `agents/openai.yaml` with `allow_implicit_invocation: false` | User-only | | Claude `allowed-tools` | Kept with a notice; it grants no Motif permission | | `.claude-plugin/marketplace.json`, `.agents/plugins/marketplace.json` | Browsable catalogs for both clients | | Host-specific hooks, forks, model switches | Reported as unsupported; the skill is not run half-way | ### Add skills **By asking.** Paste a skill link with a clear request. The built-in `skill-setup` inspects the source, installs the skill and checks it: > Install this skill for this project: https://github.com/anthropics/skills/tree/main/skills/webapp-testing Asking for it "globally" or "for all projects" installs into `~/.motif/`, for every project. `/skill-setup <source or request>` runs it explicitly, including for a Claude or Codex skill you already have. **From a link, a repository or a folder.** ```bash motif skills add https://github.com/anthropics/skills/tree/main/skills/webapp-testing motif skills add https://github.com/anthropics/skills/blob/main/skills/brand-guidelines/SKILL.md --scope project motif skills add anthropics/skills --path skills/webapp-testing motif skills add ./my-skill --scope project motif skills inspect ./my-skill # preview without installing ``` A GitHub folder, `SKILL.md` or raw link installs the whole skill folder. `--ref` pins a branch, tag or commit, `--dry-run` previews, and the resolved commit and content digest are recorded with each installation. **From Claude Code or Codex.** ```bash motif skills import claude # list candidates; nothing is copied yet motif skills import codex --json motif skills import claude --skill webapp-testing --scope project ``` Claude import reads `~/.claude/skills`, the project's `.claude/skills` and the plugins enabled in Claude Code. Codex import reads `~/.agents/skills`, `~/.codex/skills`, the project's `.agents/skills` up to the Git root and the plugins enabled in Codex. Skills are copied into Motif's own store; the other client's files and settings are never changed. **From a marketplace.** ```bash motif skills marketplace OWNER/CATALOG motif skills add OWNER/CATALOG --plugin ENTRY --skill SKILL_NAME ``` **A plugin package with its own MCP servers.** `motif plugins add OWNER/REPO --skill NAME` installs its skills, `motif plugins inspect NAME` shows the servers it brings, and `motif plugins connect NAME --login` registers and connects them after you approve. Hooks, agents and commands written for another host stay inactive. `/plugin-setup <source or request>` does the same by request. **Write your own.** Create `~/.motif/skills/<name>/SKILL.md` for every project, or `<project>/.motif/skills/<name>/SKILL.md` for one; `/skill-creator` can draft it. ```markdown --- name: explain-widget description: Explain this project's widget lifecycle and check its invariants. --- Read references/lifecycle.md relative to this skill's directory. Explain the widget named in $ARGUMENTS, citing the relevant source. ``` `motif skills installed`, `motif skills update NAME` and `motif skills remove NAME` maintain installed copies. Restart a running session to load newly installed skills. The [skills guide](docs/skills.md) has the precedence rules and the full compatibility table. ### Built-in workflow bundles Five plugins ship with Motif. Their skills run as slash commands in every project, and their instructions and references load only when used. A bundle tied to an MCP service is listed for the model only while that server is enabled. User and project skills can override them, and listing plugins never starts a service. | Bundle | Skills | Optional service | |---|---|---| | `library-docs` | `/library-docs` | Context7 | | `browser-web-testing` | `/browser-testing` | Playwright | | `github-workflow` | `/github-workflow` | GitHub MCP or an authenticated `gh` CLI | | `frontend-quality` | `/frontend-quality`, `/react-composition` | Context7 and Playwright | | `mcp-builder` | `/mcp-builder` | The server being developed | ```bash motif plugins list motif plugins inspect library-docs --json motif plugins connect library-docs ``` Connecting a bundle's service is a separate step you approve; `--yes` confirms a reviewed plan in a noninteractive shell. Existing registrations are preserved, and a bundle being available does not mean its service is signed in. See [bundled workflows](docs/skills.md#built-in-workflow-bundles). --- ## Choose a provider and get an API key First launch offers Infron and Morphfactory (BETA). Existing sessions keep their current connection; use `/provider` or the provider row in `/config` to switch. Both use the model id `motif/motif-3` and an OpenAI-compatible endpoint: | provider | base URL | API key environment variable | |---|---|---| | Infron | `https://llm.onerouter.pro/v1` | `MOTIF_API_KEY` | | Morphfactory (BETA) | `https://api-cbt.morphfactory.io/v1` | `MOTIF_MORPHFACTORY_API_KEY` | 1. Create a key at [Infron's API Keys dashboard](https://infron.ai/dashboard/apiKeys) or [Morphfactory's console](https://cbt.morphfactory.io/console?view=keys). 2. Run `motif`, choose the provider and paste its key. A one-token request checks it before saving it to `~/.motif/.env` (readable only by you). Provider keys are stored separately, so switching or `/logout` preserves the other key. 3. In a script, use `motif login --provider morphfactory`, then `motif --provider morphfactory -p "your question"`. `--provider infron` selects Infron; explicit `--endpoint` and `--model` flags override the preset. 4. `motif doctor --provider morphfactory` checks the connection, tool calls, reasoning and prefix caching. Infron's account balance is only available with Infron; local session token usage remains available for both providers. Environment variables or a project `.env` work too; `--env-file <path>` reads that file first. Set `MOTIF_ENDPOINT` to select a provider through an env file. Infron remains the default when no provider is configured. Only `MOTIF_*` keys are read from a `.env` file, none of them are exported, and the key is removed from the harness's own environment before anything is spawned — the agent's `bash` cannot see it, and neither can a project hook. --- ## Commands and keys | command | what it does | |---|---| | `/help` | commands and keys | | `/status` (`/cost`) | connection, settings and session totals | | `/config` | edit settings in the dashboard; `/config show` lists values and sources | | `/stats` | task and tool statistics from local session journals | | `/usage` | Infron balance, recorded token usage and reported request costs | | `/doctor` | probe the endpoint: auth, parsers, cache, channels | | `/mcp [list\|connect NAME\|disconnect NAME\|reconnect NAME\|login NAME\|logout NAME]` | open the MCP manager to add a preset, or inspect, control and sign in to a connection | | `/mcp-setup <URL>` | use the built-in skill to register and check an MCP server | | `/provider [infron\|morphfactory]` | choose a provider, preserving each provider's key | | `/login`, `/logout` | check and save the selected provider's key to `~/.motif/.env`; remove that saved key | | `/model [id]`, `/endpoint [url]` | show or set the model id or endpoint for the next task | | `/channel [toolcall\|object\|raw]` | show or set the action channel; changing it restarts the conversation | | `/max-turns [n]`, `/max-tokens [n\|off]`, `/seed [n\|off]` | per-task ceilings and the sampling seed | | `/theme [name]` | show, list or set the colour theme | | `/thinking` | show or hide the model's reasoning | | `/compact [focus]` | replace the transcript with the model's summary of it; words after it say what to keep | | `/compact-at [0.5-1]` | the context fraction at which compaction runs (default 0.75) | | `/permissions [ask\|auto]` | ask before commands, writes and patches run, or run everything | | `/cwd [path]` | show or change the working directory | | `/notes` (`/memory`), `/hooks` | the project notes every task reads; the hooks around tools | | `/skills`, `/agents`, `/plugins` | what is loaded; each skill also runs as `/<skill> [input]` | | `/skill-setup <source or request>` | inspect, install and verify skills from local files, clients or marketplaces | | `/plugin-setup <source or request>` | install a Claude/Codex plugin package's skills and connect its MCP servers | | `/new` (`/clear`) | start a new conversation; the working tree is untouched | | `/sessions`, `/resume [n\|file]` | recorded sessions; continue from one | | `/quit` (`/exit`, `/q`) | leave | ``` enter send · \ + enter newline · esc interrupt or clear · ctrl-c twice quit · ctrl-d quit ↑ ↓ history · tab show or hide reasoning · ctrl-o output viewer · ctrl-l redraw · shift-tab permissions @ attach a file · ! run a shell line · # add a project note · / commands · ? hide this ``` Tool results show a three-row preview by default, including long single-line JSON and errors. `Ctrl+O` opens the full output in a read-only transcript viewer. Use ↑/↓, PageUp/PageDown or Home/End to browse, then Esc, `q` or `Ctrl+O` to return to the same draft and scrollback. This does not truncate the model's tool data. `--verbose` or `/config verbose true` explicitly keeps full inline output. The Infron balance connects automatically using the key entered at first login. Press `r` in Usage to refresh. The account balance and costs recorded in local journals are separate: unreported or unrecorded charges are not estimated. --- ## Features | area | what you get | |---|---| | Session | Replies stream in as the model writes; reasoning stays out of the transcript unless `--thinking` or `/thinking` asks for it; tool calls behind `⏺`, results under `⎿`; a status line with context used and the prefix-cache ratio | | Input | `@path` attaches a file or a directory listing, with a picker as you type; `@skill:name` attaches a skill's instructions; `!command` runs a shell line and shows the model its output; `#note` appends to `.motif/NOTES.md`; `\` + Enter for a newline; long pastes collapsed; Hangul and other wide text handled by display width; ↑↓ history | | Commands | `/` opens a menu of every setting; a change made at the prompt is saved to `~/.motif/settings.json`; skills run as commands (`/commit fix the parser`); `?` lists the keys | | Permissions | A numbered prompt before a command, a write, a patch or the terminal runs; "don't ask again for this tool"; a refusal the model is told about; Shift-Tab or `/permissions auto` runs everything | | Conversation | Each task sees the ones before it; `--continue` and `/resume` bring a recorded conversation back; messages sent while a task runs are queued; Esc interrupts; Codex-style compaction past `compactAt` of the window — the model writes a handoff summary and your own messages are kept verbatim — and `/compact <focus>` on demand | | Backend | `.motif/` laid out like Claude Code's `.claude/`: user and project settings, skills, agents, plugins, notes, one journal per task, history; project hooks applied once `motif trust` approves them | | Skills and agents | 18 core skills (`explore`, `plan`, `explain`, `code-review`, `security-review`, `test-fix`, `debug`, `refactor`, `commit`, `pr-body`, `docs`, `init`, `skill-creator`, `skill-setup`, `plugin-setup`, `mcp-setup`, `motif-endpoint`, `korean`); 6 additional skills in five built-in workflow bundles; Claude Code and Codex skills and plugins installed from links, repositories, marketplaces or the clients themselves ([Skills](#skills)); 5 built-in subagents (`explorer`, `reviewer`, `tester`, `planner`, `patcher`) | | MCP | stdio, Streamable HTTP and legacy SSE servers; 8 built-in presets set up from `/mcp` without a restart; CLI registration and Codex/Claude config import; `mcp-setup` for setup by request; browser OAuth (`--no-browser` for SSH), GitHub through `gh`, human form/URL approval; server tools follow session permissions ([MCP servers](#mcp-servers)) | | Endpoint | The key asked for once and saved to `~/.motif/.env`, withheld from every command the agent runs; a 401 that says which side of the key it is on; a 429 retried after the server's `Retry-After`; `motif doctor` reports what the server actually returns | | Screen | Shrinking the window mid-session leaves no stale rows; five themes (`motif`, `claude`, `mono`, `solarized`, `dracula`) swapped in place | | Scripts | `motif -p "question"` prints only the reply; `motif "task"` runs one task and exits | Skills are covered in [Skills](#skills). A subagent is Markdown with frontmatter — `name`, `description`, `tools` (a count, or a prefix of the canonical list), `readOnly`, `maxTurns`. A plugin is a directory with `plugin.json` and its own `skills/` and `agents/`. ``` ~/.motif/settings.json your defaults: model, endpoint, channel, budgets, theme, thinking, compactAt, permissions ~/.motif/.env the credential ~/.motif/mcp.json MCP server registrations ~/.motif/auth/ MCP sign-in credentials and delegation grants, private to you ~/.motif/skills/<n>/SKILL.md, ~/.motif/agents/<n>.md yours, on every project ~/.motif/skills-installed.json, ~/.motif/skill-packages/ managed skill copies and sources <repo>/.motif/settings.json the project's settings and hooks — applied once `motif trust` approves it <repo>/.motif/skills/, agents/, NOTES.md the project's ~/.motif/plugins/<n>/, <repo>/.motif/plugins/<n>/ plugin.json + skills/ + agents/ <repo>/.motif/sessions/*.jsonl one journal per task <repo>/.motif/history.jsonl what you typed, for ↑ ``` --- ## Built around Motif-3 A generic harness assumes the model's tool calls parse, that the tool list is free to change, and that reasoning is optional. None of that holds for Motif-3, and each fact below, checked rather than assumed, became a design constraint. | Fact about Motif-3 | Source | What it forces here | |---|---|---| | The chat template renders the tools block **before** the system prompt, in the same turn; reordering two tools leaves ~24% of the prefix | `chat_template.jinja`; measured in `template.test.ts` | Nine tools in a frozen, canonical order (`done, bash, read, write, apply_patch, term, skill, task, mcp`); a subagent takes a *prefix* of it; a prompt under 3k tokens (about 2k for a one-shot run without the MCP tool) of which 90–98% is served from the endpoint's cache | | Intermediate reasoning is rendered only when tools are registered, and the hosted router does render returned `reasoning_content` | template, measured; endpoint, 2026-09-20 | Tools are registered on every channel, and the model's reasoning is sent back every turn | | JSON inside `<tool_call>` is frequently malformed (shell `\$`, regex `\s`), and the hosted endpoint sometimes emits a bare call with no tags | the vendor's vLLM parser; endpoint, measured | A client-side repair ladder behind the server's own, recovery of bare calls, a breakage budget, and closed tool schemas enforced by a linter that fails the build | | A dropped tool call and a final answer look the same | vendor parser comments; measured in the campaign | `done` is a tool; in benchmark mode a turn without an action is handed back instead of ending the task | | SWE-bench Verified 76.2 came from a single `bash` tool; Terminal-Bench 2.1 74.9 from a persistent tmux session | mini-SWE-agent config; Terminus 2 | The thin tool set is the baseline, with a `term` tool beside `bash` | | A reasoning step takes 200–300 s on the hosted endpoint | measured | No 300-second header timeout in the transport; a 429 is retried after `Retry-After` | | The hosted endpoint has no `/v1/completions` | `motif doctor` | Only the native `toolcall` channel runs there; the `object` and `raw` channels and the pruning toolkit need a local completions server (`--experimental-channel`) | Whatever the channel, the model's own body is kept verbatim in the transcript, and the loop is tested by injecting the faults the model actually produces: invalid escapes, truncated calls, unparseable bodies, empty turns, a dead server. Motif-3 is a 314B-parameter mixture-of-experts model with 13.2B activated per token and a native 256K context, released under MIT by [Motif Technologies](https://motiftech.io): [weights](https://huggingface.co/Motif-Technologies/Motif-3), [technical report](https://arxiv.org/abs/2608.09119), [serving fork](https://github.com/MotifTechnologies/vllm) with the `motif` tool-call parser, and the [Infron API](https://infron.ai/models/motif/motif-3) used here, which also serves `/v1/responses` and Anthropic-style `/v1/messages`, so Codex, Claude Code and other harnesses reach the same model. --- ## Benchmark > Aider polyglot alone cannot settle the comparison. It measures spec-to-code > with a test loop in a two-file repository, one run per instance. SWE-bench > Verified and Terminal-Bench 2.1, the benchmarks behind Motif-3's published > scores, still need to be run with the same three harnesses before the gap > can be called general. <img src="docs/benchmark.svg" alt="Motif-3 on the Aider polyglot benchmark: Motifcode 92.0%, OpenCode 83.1%, Codex 79.8% pass rate over 213 instances, with per-language results" width="912"> The claim above was measured on 2026-09-20/21: the same model behind three harnesses on the Aider polyglot benchmark — 213 Exercism exercises across C++, Go, Java, JavaScript, Python and Rust (225 minus 12 excluded before the run), one attempt per instance, seed 0, a 15-minute cap, the same task text, and the same grader applying each patch to a pristine checkout. Motifcode ran in benchmark mode as shipped; Codex CLI and OpenCode ran through thin adapters against the same Infron endpoint. | harness | passed | pass rate (95% CI) | vs. Motifcode, paired | McNemar p | |---|---|---|---|---| | **Motifcode 0.3.0** + Motif-3 | **196** / 213 | **92.0%** (87.6–95.0) | — | — | | OpenCode 1.17.9 + Motif-3 | 177 / 213 | 83.1% (77.5–87.5) | −8.9 pp (−14.6, −3.8) | 0.003 | | Codex CLI 0.154.0 + Motif-3 | 170 / 213 | 79.8% (73.9–84.7) | −12.2 pp (−17.4, −7.0) | < 0.001 | The gap is the harness, not the model. Codex ended 38 rows on the time cap and 2 on a malformed tool call echoed back into history; OpenCode ended 21 on the router's repetition abort and 18 on the cap; Motifcode ended 22 on the cap and 9 on its own turn and loop guards, and 182 normally. One seed at temperature 1.0, so differences under ~8 pp are not resolved; Codex ran with its stream idle timeout raised (stock 300 s dropped the stream on this endpoint's long reasoning steps), OpenCode with web tools denied. Method, per-language results, every row and the incident log are in [`packages/eval/REPORT.md`](packages/eval/REPORT.md); the adapters and scripts to repeat the run with your own key are in [`packages/eval/polyglot-bench/`](packages/eval/polyglot-bench/). --- ## Repository ``` packages/protocol/ chat template · tool-call repair · reasoning scrubber · channels packages/tools/ the frozen tool set and its linter packages/core/ agent loop · endpoint config · compaction · breakage budget · loop guard packages/replay/ record, replay and deliberately break the transport packages/tui/ typed cells · two-region streaming · composer · menus · themes packages/mcp/ MCP client and manager · presets · OAuth and GitHub CLI sign-in · schema checks packages/skills/ Claude/Codex-compatible skill parsing, the registry and the built-in skills packages/agents/ subagent definitions and the local scheduler packages/hooks/ lifecycle shell hooks packages/journal/ append-only session log, resume, trajectory export packages/cli/ the `motif` command, the interactive session, login, doctor, MCP/skill/plugin setup packages/eval/ polyglot suite, campaign runner, worktree grader, REPORT.md and the polyglot-bench/ kit (the benchmark above) toolkit/ prompt goldens (jinja2), expert-pruning surgery, campaign score table corpus/ vendored template + generated goldens docs/ logo, screenshots, benchmark figure, model guide, MCP and skills guides ``` ```bash pnpm install && pnpm typecheck && pnpm build pnpm test # unit, integration, CLI end-to-end, and an install smoke pnpm lint:tools # schema linter — fails the build on loose schemas ``` To release, bump `version` in both `package.json` files and `VERSION` in `packages/cli/src/main.ts`, commit, and push a tag (`git tag v0.3.0 && git push origin v0.3.0`); the release workflow runs the suite and publishes to npm through trusted publishing, with provenance and no stored token. Prior art read closely: [Claude Code](https://docs.anthropic.com/en/docs/claude-code) for the session's shape; [Codex](https://github.com/openai/codex) for typed history cells, two-region streaming and the compaction handoff; [gemini-cli](https://github.com/google-gemini/gemini-cli) for approval queues and loop detection; [hermes-agent](https://github.com/NousResearch/hermes-agent) for the streaming think-scrubber; [Terminus 2](https://github.com/harbor-framework/terminal-bench-1) for the persistent-terminal contract; [mini-SWE-agent](https://github.com/SWE-agent/mini-swe-agent) for proof that a thin tool set is enough. --- ## Developer **Taewoo Park** — physics and spintronics at KAIST, building harnesses for science and code. [taewoopark.com](https://taewoopark.com) · [GitHub](https://github.com/TaewoooPark) · [X](https://x.com/theoverstrcture) · [LinkedIn](https://www.linkedin.com/in/taewoo-park-427a05352) --- ## Licence Apache-2.0. The Motif-3 weights and chat template are MIT, from [Motif-Technologies/Motif-3](https://huggingface.co/Motif-Technologies/Motif-3); any derived checkpoint inherits that licence and credits the original. Motifcode is not affiliated with Motif Technologies or Infron.

Cargando el README del repositorio…

Skills en este repositorio

clasificación pendiente

skill

ocupación

descripción

actualizado

browser-testing

sin clasificar

Reproduce web UI bugs and verify browser workflows with Playwright MCP or the project's existing browser tests.