{"id":49002673,"url":"https://github.com/coreason-ai/coreason-runtime","last_synced_at":"2026-05-24T02:03:20.475Z","repository":{"id":346469062,"uuid":"1190093790","full_name":"CoReason-AI/coreason-runtime","owner":"CoReason-AI","description":"The official zero-trust, high-throughput kinetic execution engine for the coreason-manifest ontology.","archived":false,"fork":false,"pushed_at":"2026-05-19T17:57:44.000Z","size":5598,"stargazers_count":1,"open_issues_count":1,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-19T19:17:44.549Z","etag":null,"topics":["active-inference","agents","artificial-intelligence","constrained-decoding","coreason","kinetic-execution","llm","mcp","ontology","orchestration","temporal","wasm","zero-trust"],"latest_commit_sha":null,"homepage":"https://coreason-ai.github.io/coreason-runtime/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/CoReason-AI.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":"NOTICE","maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-03-24T00:49:47.000Z","updated_at":"2026-05-19T17:46:57.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/CoReason-AI/coreason-runtime","commit_stats":null,"previous_names":["coreason-ai/coreason-runtime"],"tags_count":101,"template":false,"template_full_name":null,"purl":"pkg:github/CoReason-AI/coreason-runtime","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CoReason-AI%2Fcoreason-runtime","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CoReason-AI%2Fcoreason-runtime/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CoReason-AI%2Fcoreason-runtime/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CoReason-AI%2Fcoreason-runtime/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CoReason-AI","download_url":"https://codeload.github.com/CoReason-AI/coreason-runtime/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CoReason-AI%2Fcoreason-runtime/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33316518,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-21T12:23:38.849Z","status":"ssl_error","status_checked_at":"2026-05-21T12:22:11.673Z","response_time":62,"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":["active-inference","agents","artificial-intelligence","constrained-decoding","coreason","kinetic-execution","llm","mcp","ontology","orchestration","temporal","wasm","zero-trust"],"created_at":"2026-04-18T19:04:09.321Z","updated_at":"2026-05-24T02:03:20.448Z","avatar_url":"https://github.com/CoReason-AI.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🧠 coreason-runtime\n\n[![PyPI - Version](https://img.shields.io/pypi/v/coreason_runtime.svg)](https://pypi.org/project/coreason_runtime)\n[![CI](https://github.com/CoReason-AI/coreason-runtime/actions/workflows/ci.yml/badge.svg?branch=main)](https://github.com/CoReason-AI/coreason-runtime/actions/workflows/ci.yml)\n[![Documentation](https://img.shields.io/badge/docs-GitHub_Pages-blue.svg)](https://coreason-ai.github.io/coreason-runtime/)\n[![Deploy Docs](https://github.com/CoReason-AI/coreason-runtime/actions/workflows/docs.yml/badge.svg)](https://github.com/CoReason-AI/coreason-runtime/actions/workflows/docs.yml)\n[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/coreason_runtime.svg)](https://pypi.org/project/coreason_runtime)\n[![Downloads](https://img.shields.io/pypi/dm/coreason_runtime.svg)](https://pypi.org/project/coreason_runtime/)\n[![License: Prosperity 3.0](https://img.shields.io/badge/License-Prosperity_3.0-blue.svg)](https://prosperitylicense.com/versions/3.0.0)\n[![SOTA: 2026](https://img.shields.io/badge/Architecture-Kinetic_Engine-purple.svg)](https://coreason.ai)\n\u003cbr\u003e\n[![OpenSSF Scorecard](https://img.shields.io/ossf-scorecard/github.com/CoReason-AI/=OpenSSF)](https://scorecard.dev/viewer/?uri=github.com/CoReason-AI/coreason-runtime)\n[![Code Coverage](https://img.shields.io/codecov/c/github/CoReason-AI/coreason-runtime/main.svg)](https://codecov.io/gh/CoReason-AI/coreason-runtime)\n[![Checked with mypy](https://www.mypy-lang.org/static/mypy_badge.svg)](https://mypy-lang.org/)\n[![Code style: ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)\n[![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit)](https://github.com/pre-commit/pre-commit)\n[![Security: Bandit](https://img.shields.io/badge/security-bandit-yellow.svg)](https://github.com/PyCQA/bandit)\n\u003cbr\u003e\n[![uv](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/uv/main/assets/badge/v0.json)](https://github.com/astral-sh/uv)\n[![Forks](https://img.shields.io/github/forks/CoReason-AI/coreason-runtime.svg)](https://github.com/CoReason-AI/coreason-runtime/network/members)\n[![Powered By: AI](https://img.shields.io/badge/Powered%20By-CoReason%20AI-FF4500.svg)](https://coreason.ai)\n[![OSV-Scanner](https://img.shields.io/github/actions/workflow/status/CoReason-AI/coreason-runtime/osv-scanner.yml?branch=main\u0026label=OSV-Scanner)](https://github.com/CoReason-AI/coreason-runtime/actions/workflows/osv-scanner.yml)\n[![Trivy](https://img.shields.io/github/actions/workflow/status/CoReason-AI/coreason-runtime/trivy.yml?branch=main\u0026label=Trivy)](https://github.com/CoReason-AI/coreason-runtime/actions/workflows/trivy.yml)\n[![TruffleHog](https://img.shields.io/github/actions/workflow/status/CoReason-AI/coreason-runtime/trufflehog.yml?branch=main\u0026label=TruffleHog)](https://github.com/CoReason-AI/coreason-runtime/actions/workflows/trufflehog.yml)\n[![OWASP ZAP](https://img.shields.io/github/actions/workflow/status/CoReason-AI/coreason-runtime/dast.yml?branch=main\u0026label=OWASP%20ZAP)](https://github.com/CoReason-AI/coreason-runtime/actions/workflows/dast.yml)\n\n**The official zero-trust, high-throughput kinetic execution engine for the `coreason-manifest` ontology.**\n\n`coreason-runtime` is a State-of-the-Art (SOTA) 2026 cybernetic execution engine. It abandons legacy, fragile \"chain-of-thought\" LLM scripting in favor of deterministic **Active Inference**, Topological Data Analysis (TDA), and strictly bounded Markov Decision Processes. It is the definitive implementation of the CoReason Tripartite Doctrine for Tier-1 Kinetic Execution.\n\nIf `coreason-manifest` is the DNA of your multi-agent topologies, `coreason-runtime` is the biological cell that safely executes them.\n\n---\n\n## 🚀 The Paradigm Shift\n\nModern enterprise AI cannot rely on unbounded `while True` loops and raw Python `exec()`. The `coreason-runtime` enforces mathematical rigor at every boundary:\n\n* **Deterministic Orchestration:** Built on **Temporal**, Cognitive Topology executions are durably serialized. If a GPU dies or a network request fails, the topology pauses, rehydrates, and resumes exactly where it left off. No amnesia. No ghost processes.\n* **Zero-Trust WASM Sandboxing:** Kinetic actions (Tools) are executed inside isolated WebAssembly environments via **Extism**. Agents can execute complex IO without ever touching your host's root kernel or filesystem.\n* **Epistemic Vector Ledger:** Native, zero-copy integration with **LanceDB**. The runtime automatically projects the agent's latent state into an embedded vector memory layer.\n* **Embedded Medallion Analytics:** No need for heavy Spark clusters. Raw telemetry (SSE) is ingested via **dlt** and transformed into Silver/Gold analytical intelligence matrices using Rust-backed **Polars** directly inside the daemon.\n* **Human-in-the-Loop (HITL) Webhooks:** When an agent calculates high Variational Free Energy (epistemic uncertainty), it durably suspends its thread and emits an Oracle Request, waiting safely for a human expert to inject resolving priors via API.\n* **Bipartite Proposer-Verifier Protocol:** The runtime is physically isolated from local OS capability generation. To fabricate assets, the runtime strictly proposes topological models over air-gapped MCP boundaries to the remote Universal Asset Forge (`coreason-meta-engineering`).\n\n---\n\n## ⚡ Installation\n\nWe utilize `uv` for ultra-fast, deterministic resolution. Ensure you are running Python 3.14+.\n\n```bash\nuv add coreason-runtime\n```\n\n*Note: For bare-metal enterprise deployment with SGLang GPU passthrough, refer to our [Docker Deployment Guide](docs/DEPLOYMENT.md).*\n\n------\n\n## 🐳 Docker Deployment \u0026 Hardware Capabilities\n\nThe local docker development environment dynamically scales its container footprint depending on the capabilities of the host system.\n\nIf the host system does not have an NVIDIA GPU, it skips the heavy `sglang` (Cognitive Engine) image download (10GB+) and installs a lightweight `runtime` package without CUDA/PyTorch dependencies.\n\nTo automatically configure your environment based on host capabilities, run:\n\n### Windows (PowerShell)\n```powershell\n./scripts/detect_capabilities.ps1\n```\n\n### macOS/Linux\n```bash\nchmod +x ./scripts/detect_capabilities.sh\n./scripts/detect_capabilities.sh\n```\n\nThese scripts will automatically inspect your hardware and generate/update the local `.env` configuration file with:\n- `COMPOSE_PROFILES=gpu` (activated only if NVIDIA GPU is detected)\n- `EXTRAS=inference` (packages deep learning libraries only if GPU is present)\n\nAfter running the capability check, start the local stack:\n```bash\ndocker compose up --build\n```\n\n\n------\n\n## 🛠️ Quickstart\n\nThe runtime is designed to be operated via its CLI or mounted as an API edge.\n\n### 1\\. Run a Local Cognitive Topology\n\nTo execute a mathematically verified agentic topology, simply pass the JSON/YAML manifest to the runtime:\n\n```bash\ncoreason run ./my_topology_manifest.json\n```\n\n### 2\\. Boot the API Edge \u0026 Telemetry Broker\n\nTo boot the runtime as a continuous daemon (exposing the CRDT State Sync, Schema Projection, and Server-Sent Events telemetry):\n\n```bash\ncoreason serve --port 8000\n```\n\nYour frontend IDE can now connect to `http://localhost:8000/api/v1/telemetry/stream` to visualize the active inference loops in real-time.\n\n-----\n\n## 🏗️ Architecture\n\nThe runtime operates across five isolated computational boundaries under the CoReason Tripartite Doctrine:\n\n1.  **The Orchestrator:** Temporal Python SDK running deterministic AST-scanned workflows.\n2.  **The Cognitive Engine:** SGLang routing for sub-millisecond constrained tensor inference.\n3.  **The Kinetic Sandbox:** Extism executing `.wasm` tools with zero-trust lattices.\n4.  **The Epistemic Store:** LanceDB \u0026 Polars managing long-term vectors and ETL metrics.\n5.  **The Universal Asset Forge:** A decoupled MCP channel connecting strictly to the `coreason-meta-engineering` Fabrication Lines to physically synthesize assets via the Bipartite generation pipeline.\n\nFor a deep dive into the cybernetic loop, read the [Architecture Documentation](docs/architecture.md).\n\n-----\n\n## 📜 License\n\nThis software is proprietary and dual-licensed under the **Prosperity Public License 3.0**.\nCommercial use beyond a 30-day trial requires a separate commercial license. See the `LICENSE` file for details.\n\nCopyright (c) 2026 CoReason, Inc.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcoreason-ai%2Fcoreason-runtime","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcoreason-ai%2Fcoreason-runtime","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcoreason-ai%2Fcoreason-runtime/lists"}