{"id":36974781,"url":"https://github.com/reasonkit/reasonkit","last_synced_at":"2026-01-13T22:02:11.617Z","repository":{"id":331378901,"uuid":"1126400457","full_name":"reasonkit/reasonkit","owner":"reasonkit","description":"\"From Prompt to Cognitive Engineering\". — AI: Designed, not Dreamed.","archived":false,"fork":false,"pushed_at":"2026-01-03T16:03:00.000Z","size":60411,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-01-07T06:14:49.093Z","etag":null,"topics":["agentic-ai","ai","ai-agents","async","browser-automation","cli","cognitive-architecture","developer-tools","embeddings","llm","llm-tools","mcp","model-context-protocol","rag","reasoning","rust","semantic-search","tokio","vector-database","web-scraping"],"latest_commit_sha":null,"homepage":"https://ReasonKit.sh","language":"Rust","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/reasonkit.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":".github/CODEOWNERS","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":null,"dco":null,"cla":null}},"created_at":"2026-01-01T20:45:00.000Z","updated_at":"2026-01-03T16:03:01.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/reasonkit/reasonkit","commit_stats":null,"previous_names":["reasonkit/reasonkit"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/reasonkit/reasonkit","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reasonkit%2Freasonkit","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reasonkit%2Freasonkit/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reasonkit%2Freasonkit/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reasonkit%2Freasonkit/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/reasonkit","download_url":"https://codeload.github.com/reasonkit/reasonkit/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/reasonkit%2Freasonkit/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28400446,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-13T14:36:09.778Z","status":"ssl_error","status_checked_at":"2026-01-13T14:35:19.697Z","response_time":56,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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-ai","ai","ai-agents","async","browser-automation","cli","cognitive-architecture","developer-tools","embeddings","llm","llm-tools","mcp","model-context-protocol","rag","reasoning","rust","semantic-search","tokio","vector-database","web-scraping"],"created_at":"2026-01-13T22:02:11.044Z","updated_at":"2026-01-13T22:02:11.612Z","avatar_url":"https://github.com/reasonkit.png","language":"Rust","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\n# ReasonKit\n\n**The Reasoning Engine — Auditable Reasoning for Production AI**\n\n[![CI](https://badges.reasonkit.sh/github/actions/workflow/status/reasonkit/reasonkit/ci.yml?branch=main\u0026style=flat-square\u0026logo=github\u0026label=CI\u0026color=06b6d4\u0026logoColor=06b6d4)](https://github.com/reasonkit/reasonkit/actions/workflows/ci.yml)\n[![Security](https://badges.reasonkit.sh/github/actions/workflow/status/reasonkit/reasonkit/security.yml?branch=main\u0026style=flat-square\u0026logo=github\u0026label=Security\u0026color=10b981\u0026logoColor=10b981)](https://github.com/reasonkit/reasonkit/actions/workflows/security.yml)\n[![Crates.io](https://badges.reasonkit.sh/crates/v/reasonkit?style=flat-square\u0026logo=rust\u0026color=f97316\u0026logoColor=f9fafb)](https://crates.io/crates/reasonkit)\n[![docs.rs](https://badges.reasonkit.sh/docsrs/reasonkit?style=flat-square\u0026logo=docs.rs\u0026color=06b6d4\u0026logoColor=f9fafb)](https://docs.rs/reasonkit)\n[![Downloads](https://badges.reasonkit.sh/crates/d/reasonkit?style=flat-square\u0026color=ec4899\u0026logo=rust\u0026logoColor=f9fafb)](https://crates.io/crates/reasonkit)\n[![License](https://badges.reasonkit.sh/static/v1?label=license\u0026message=Apache%202.0\u0026color=a855f7\u0026style=flat-square\u0026labelColor=030508)](LICENSE)\n[![Rust](https://badges.reasonkit.sh/static/v1?label=rust\u0026message=1.75%2B\u0026color=f97316\u0026style=flat-square\u0026logo=rust\u0026logoColor=f9fafb)](https://www.rust-lang.org/)\n\n_Meta-crate providing unified installation for the complete ReasonKit suite_\n\n[Documentation](https://docs.rs/reasonkit) | [Crates.io](https://crates.io/crates/reasonkit) | [Website](https://reasonkit.sh)\n\n\u003c/div\u003e\n\n**ReasonKit** transforms ad-hoc LLM prompting into structured, auditable reasoning chains. This meta-crate provides a unified installation for the complete ReasonKit suite.\n\n## One-Line Install\n\n```bash\n# Install complete ReasonKit suite\ncargo install reasonkit\n\n# Or use the universal installer\ncurl -fsSL https://get.reasonkit.sh | bash\n```\n\nInstalling provides two equivalent binaries:\n\n- `reasonkit` — Full command name\n- `rk` — Short alias for faster typing\n\n## What's Included\n\n| Component  | Crate                                                     | Purpose                                     |\n| ---------- | --------------------------------------------------------- | ------------------------------------------- |\n| **Core**   | [reasonkit-core](https://crates.io/crates/reasonkit-core) | Reasoning engine with ThinkTools            |\n| **Memory** | [reasonkit-mem](https://crates.io/crates/reasonkit-mem)   | Vector storage, hybrid search, RAPTOR trees |\n| **Web**    | [reasonkit-web](https://crates.io/crates/reasonkit-web)   | Browser automation, MCP sidecar             |\n\n## Quick Start\n\n### CLI Usage\n\nUse `reasonkit` or the short alias `rk` — they're identical:\n\n```bash\n# Run structured reasoning (ThinkTools)\nrk think --profile balanced \"Should we migrate to microservices?\"\n\n# Quick 2-step analysis\nrk think --profile quick \"Is this email phishing?\"\n\n# Maximum rigor (paranoid mode)\nrk think --profile paranoid \"Validate this cryptographic implementation\"\n\n# Verify claims with triangulation\nrk verify \"GPT-4 has 1.76 trillion parameters\"\n\n# Start MCP server for AI agent integration\nrk serve\n```\n\n### Library Usage\n\n```rust\nuse reasonkit::prelude::*;\n\n#[tokio::main]\nasync fn main() -\u003e anyhow::Result\u003c()\u003e {\n    // Create reasoning executor\n    let executor = reasonkit::core::thinktool::ProtocolExecutor::new()?;\n\n    // Run GigaThink for multi-perspective analysis\n    let result = executor.execute(\n        \"gigathink\",\n        reasonkit::core::thinktool::ProtocolInput::query(\"What factors drive startup success?\")\n    ).await?;\n\n    println!(\"Confidence: {:.1}%\", result.confidence * 100.0);\n    for step in \u0026result.steps {\n        println!(\"- {}\", step.as_text().unwrap_or_default());\n    }\n\n    Ok(())\n}\n```\n\n## ThinkTools\n\nFive core reasoning protocols:\n\n| Tool              | Shortcut | Purpose                                          |\n| ----------------- | -------- | ------------------------------------------------ |\n| **GigaThink**     | `gt`     | Generate 10+ diverse perspectives                |\n| **LaserLogic**    | `ll`     | Precision deductive reasoning, fallacy detection |\n| **BedRock**       | `br`     | First principles decomposition                   |\n| **ProofGuard**    | `pg`     | Multi-source verification (3+ sources)           |\n| **BrutalHonesty** | `bh`     | Adversarial self-critique                        |\n\n## Profiles\n\nPre-configured protocol chains:\n\n| Profile    | ThinkTools         | Confidence | Use Case           |\n| ---------- | ------------------ | ---------- | ------------------ |\n| `quick`    | GT, LL             | 70%        | Fast analysis      |\n| `balanced` | GT, LL, BR, PG     | 80%        | Standard decisions |\n| `deep`     | All 5              | 85%        | Complex problems   |\n| `paranoid` | All 5 + validation | 95%        | High-stakes        |\n\n## Features\n\n```toml\n[dependencies]\n# Full suite (default)\nreasonkit = \"0.1\"\n\n# Core reasoning only\nreasonkit = { version = \"0.1\", default-features = false, features = [\"core\"] }\n\n# Memory layer only\nreasonkit = { version = \"0.1\", default-features = false, features = [\"mem\"] }\n\n# Web automation only\nreasonkit = { version = \"0.1\", default-features = false, features = [\"web\"] }\n```\n\n| Feature  | Description                 |\n| -------- | --------------------------- |\n| `full`   | All components (default)    |\n| `core`   | Reasoning engine only       |\n| `mem`    | Memory layer only           |\n| `web`    | Web/browser automation only |\n| `python` | Python bindings via PyO3    |\n\n## LLM Providers\n\n18+ providers supported out of the box:\n\n- **Major Cloud**: Anthropic, OpenAI, Google Gemini, Vertex AI, Azure OpenAI, AWS Bedrock\n- **Specialized**: xAI (Grok), Groq, Mistral, DeepSeek, Cohere, Perplexity\n- **Aggregation**: OpenRouter (300+ models)\n\n```bash\n# Set your API key\nexport ANTHROPIC_API_KEY=\"sk-ant-...\"\n\n# Or use a different provider\nrk think --provider openai --model gpt-4o \"Your question\"\n```\n\n## Architecture\n\n```\nreasonkit (meta-crate)\n│\n├── reasonkit-core    ─── The Reasoning Engine\n│   ├── ThinkTools\n│   ├── Protocol Executor\n│   ├── LLM Client\n│   └── MCP Server\n│\n├── reasonkit-mem     ─── Memory Infrastructure\n│   ├── Vector Storage (Qdrant)\n│   ├── Sparse Index (Tantivy)\n│   ├── Hybrid Retrieval\n│   └── RAPTOR Trees\n│\n└── reasonkit-web     ─── Web Sensing Layer\n    ├── Browser Controller\n    ├── Content Extraction\n    └── MCP Sidecar\n```\n\n## Philosophy\n\n**\"Designed, Not Dreamed\"** — Structure beats raw intelligence.\n\nReasonKit imposes systematic reasoning protocols on LLM outputs, producing more reliable, verifiable, and explainable results.\n\n## Documentation\n\n- **Website**: https://reasonkit.sh\n- **API Docs**: https://docs.rs/reasonkit\n- **Core Docs**: https://docs.rs/reasonkit-core\n- **Memory Docs**: https://docs.rs/reasonkit-mem\n- **Web Docs**: https://docs.rs/reasonkit-web\n\n## Individual Crates\n\nIf you only need specific functionality:\n\n```bash\n# Reasoning only\ncargo install reasonkit-core\n\n# Memory layer only\ncargo install reasonkit-mem\n\n# Web automation only\ncargo install reasonkit-web\n```\n\n## License\n\nApache-2.0 — See [LICENSE](LICENSE) for details.\n\n## Contributing\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.\n\n---\n\n**Turn Prompts into Protocols** | https://reasonkit.sh\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Freasonkit%2Freasonkit","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Freasonkit%2Freasonkit","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Freasonkit%2Freasonkit/lists"}