{"id":35784685,"url":"https://github.com/querymt/querymt","last_synced_at":"2026-05-30T08:03:27.752Z","repository":{"id":301490643,"uuid":"974179453","full_name":"querymt/querymt","owner":"querymt","description":"query.mt","archived":false,"fork":false,"pushed_at":"2026-05-28T20:16:53.000Z","size":12809,"stargazers_count":6,"open_issues_count":65,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2026-05-28T20:24:18.846Z","etag":null,"topics":["agentic-framework","agents","ai","llm","mcp-client"],"latest_commit_sha":null,"homepage":"https://query.mt","language":"Rust","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/querymt.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2025-04-28T11:28:45.000Z","updated_at":"2026-05-28T11:04:10.000Z","dependencies_parsed_at":"2026-04-01T19:04:27.961Z","dependency_job_id":null,"html_url":"https://github.com/querymt/querymt","commit_stats":null,"previous_names":["querymt/querymt"],"tags_count":15,"template":false,"template_full_name":null,"purl":"pkg:github/querymt/querymt","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/querymt%2Fquerymt","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/querymt%2Fquerymt/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/querymt%2Fquerymt/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/querymt%2Fquerymt/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/querymt","download_url":"https://codeload.github.com/querymt/querymt/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/querymt%2Fquerymt/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33684419,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-05-30T02:00:06.278Z","response_time":92,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agentic-framework","agents","ai","llm","mcp-client"],"created_at":"2026-01-07T07:00:04.658Z","updated_at":"2026-05-30T08:03:27.732Z","avatar_url":"https://github.com/querymt.png","language":"Rust","funding_links":[],"categories":[],"sub_categories":[],"readme":"# QueryMaTe\n[![Discord](https://img.shields.io/badge/Chat-Join%20Discord-7289da?logo=discord\u0026logoColor=white)](https://discord.gg/vArq2xssXt)\n[![Codecov](https://img.shields.io/codecov/c/github/querymt/querymt)](https://app.codecov.io/gh/querymt/querymt)\n[![GitHub contributors](https://img.shields.io/github/contributors/querymt/querymt)](https://github.com/querymt/querymt/graphs/contributors)\n[![Visual Studio Marketplace Version](https://img.shields.io/visual-studio-marketplace/v/querymt.vscode-querymt?label=VS%20Marketplace)](https://marketplace.visualstudio.com/items?itemName=querymt.vscode-querymt)\n\nA unified interface for Large Language Models (LLMs) with support for various providers via a plugin-based architecture.\n\n## Installation\n\nInstall the `qmt` and `qmtcode` binaries:\n\n```bash\ncurl -sSf https://query.mt/install.sh | sh\n```\n\nNightly channel:\n\n```bash\ncurl -sSf https://query.mt/install.sh | sh -s -- --nightly\n```\n\nWindows PowerShell:\n\n```powershell\nirm https://query.mt/install.ps1 | iex\n```\n\nWindows nightly channel:\n\n```powershell\n$env:QMT_CHANNEL='nightly'; irm https://query.mt/install.ps1 | iex\n```\n\nAdd `querymt` to your `Cargo.toml` with the `extism_host` feature:\n\n```toml\n[dependencies]\nquerymt = { version = \"0.2\", features = [\"extism_host\"] }\n```\n\n## Basic Usage\n\n```rust\nuse querymt::builder::LLMBuilder;\nuse querymt::chat::ChatMessage;\nuse querymt::plugin::{extism_impl::host::ExtismLoader, host::PluginRegistry};\n\n#[tokio::main]\nasync fn main() -\u003e Result\u003c(), Box\u003cdyn std::error::Error\u003e\u003e {\n    // 1. Initialize registry and register the Wasm loader\n    let mut registry = PluginRegistry::from_path(\"providers.toml\")?;\n    registry.register_loader(Box::new(ExtismLoader));\n\n    // 2. Build the LLM provider\n    let llm = LLMBuilder::new()\n        .provider(\"openai\")\n        .model(\"gpt-5-mini\")\n        .api_key(\"your-api-key\")\n        .build(\u0026registry)\n        .await?;\n\n    // 3. Send a message\n    let response = llm.chat(\u0026[\n        ChatMessage::user().content(\"Hello!\").build()\n    ]).await?;\n\n    println!(\"{}\", response);\n    Ok(())\n}\n```\n\n### Configuration (`providers.toml`)\n\n```toml\n[[providers]]\nname = \"openai\"\npath = \"oci://ghcr.io/querymt/openai:latest\"\n```\n\nFor a full examples-oriented setup (GHCR providers, local wasm provider builds, and run commands), see `crates/querymt/examples/README.md`.\n\n## Agent\n\nThe `querymt-agent` crate (in `crates/agent`) is the high-level agent runtime for QueryMaTe.\n\nIf you're new, the easiest way to try it is the `qmtcode` example at `crates/agent/examples/qmtcode.rs`.\nIt loads an agent from a TOML config file and can run in two modes:\n\n- `--stdio`: runs as an ACP stdio server (great for integrations and tooling)\n- `--dashboard`: runs with a local web dashboard for interactive use\n\n### Quick start\n\nFrom the workspace root:\n\n```bash\ncd crates/agent\n\n# ACP stdio mode\ncargo run --example qmtcode --features dashboard -- --stdio\n\n# Dashboard mode (default http://127.0.0.1:3000)\ncargo run --example qmtcode --features dashboard -- --dashboard\n\n# Dashboard mode on a custom address\ncargo run --example qmtcode --features dashboard -- --dashboard=0.0.0.0:8080\n```\n\nBy default it reads config from `examples/confs/coder_agent.toml`.\nYou can also pass your own config path before the mode flag.\n\n### Generate shared types\n\nFrom the workspace root:\n\n```bash\nscripts/generate-types.sh\n```\n\nThis regenerates TypeScript (and Swift when the sibling iOS repo exists) typeshare outputs.\n\n### macOS Silicon releases\n\nmacOS Silicon users who download the `qmtcode` release binary need to clear the quarantine flag before running it:\n\n```bash\nxattr -dr com.apple.quarantine qmtcode\n```\n\n## Documentation\n\nFor everything else, refer to [docs.query.mt](https://docs.query.mt).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fquerymt%2Fquerymt","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fquerymt%2Fquerymt","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fquerymt%2Fquerymt/lists"}