{"data":{"slug":"nikmcfly-mirofish-offline","name":"MiroFish-Offline","tagline":"Offline multi-agent simulation and prediction engine with Neo4j and Ollama local stack","github_url":"https://github.com/nikmcfly/MiroFish-Offline","owner":"nikmcfly","repo":"MiroFish-Offline","owner_avatar_url":"https://avatars.githubusercontent.com/u/70242477?v=4","primary_language":"Python","stars":2526,"forks":659,"topics":["ai","multi-agent","neo4j","offline","ollama","open-source","prediction","simulation","swarm-intelligence","vue"],"archived":false,"github_pushed_at":"2026-03-24T18:52:43+00:00","maintenance_label":"Slowing","stars_delta_30d":58,"url":"https://www.graphcanon.com/tools/nikmcfly-mirofish-offline","markdown_url":"https://www.graphcanon.com/tools/nikmcfly-mirofish-offline.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/nikmcfly-mirofish-offline","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=nikmcfly-mirofish-offline","description":"Offline multi-agent simulation & prediction engine. English fork of MiroFish with Neo4j + Ollama local stack.","homepage_url":"https://x.com/nikmcfly69/status/2033147482331390328","license":"AGPL-3.0","open_issues":49,"watchers":28,"ai_summary":"An open-source Python-based offline system for simulating and predicting behaviors of multi-agent systems using a local Neo4j graph database and Ollama framework.","readme_excerpt":"### Option A: Docker (easiest)\n\n```bash\ngit clone https://github.com/nikmcfly/MiroFish-Offline.git\ncd MiroFish-Offline\ncp .env.example .env\n\n---\n\n## Hardware Requirements\n\n| Component | Minimum | Recommended |\n|---|---|---|\n| RAM | 16 GB | 32 GB |\n| VRAM (GPU) | 10 GB (14b model) | 24 GB (32b model) |\n| Disk | 20 GB | 50 GB |\n| CPU | 4 cores | 8+ cores |\n\nCPU-only mode works but is significantly slower for LLM inference. For lighter setups, use `qwen2.5:14b` or `qwen2.5:7b`.\n\n---\n\n## License\n\nAGPL-3.0 — same as the original MiroFish project. See [LICENSE](./LICENSE).","github_created_at":"2026-03-14T22:54:19+00:00","created_at":"2026-07-15T11:18:06.892016+00:00","updated_at":"2026-09-20T05:16:46.243817+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"}],"tags":[{"slug":"ai","name":"ai"},{"slug":"multi-agent","name":"multi-agent"},{"slug":"neo4j","name":"neo4j"},{"slug":"offline","name":"offline"},{"slug":"ollama","name":"ollama"},{"slug":"open-source","name":"open-source"},{"slug":"prediction","name":"prediction"},{"slug":"simulation","name":"simulation"}],"trust":{"provenance":{"is_fork":false,"github_id":1182000750,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T05:16:43.458Z","maintenance":{"label":"Slowing","score":36,"methodology":"github_public_v1","releases_90d":0,"days_since_push":179,"last_release_at":null,"stars_delta_30d":58,"open_issues_delta_30d":-1},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":1,"high_count":0,"last_scan_at":"2026-07-15T11:18:08.239Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-09-20T05:16:44.494Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-09-20T05:16:44.494Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-09-20T05:16:44.494Z","managed_saas":false},"languages":{"value":["python","javascript"],"source":"github.language+package.json","observed_at":"2026-09-20T05:16:44.494Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-09-20T05:16:44.494Z"},"license_spdx":{"value":"AGPL-3.0","source":"github.license","observed_at":"2026-09-20T05:16:44.494Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"min_ram_gb":16,"requires_docker":true},"constraints":{"min_ram_gb":16,"requires_docker":true},"when_to_use":["Use MiroFish-Offline when you require simulations in an offline environment to predict behaviors of multi-agent systems with local data storage options using Neo4j.","Employ it when your project benefits from the integration of Neo4j and Ollama, offering a robust local stack for analyzing complex relationships within simulated scenarios without internet access."],"when_not_to_use":["Avoid MiroFish-Offline if real-time agent interactions are necessary as this tool operates in an offline setup.","Do not use it when your hardware limitations fall below the recommended specifications, such as less than 32 GB RAM and less than 8 cores CPU, especially for efficient LLM inference tasks."],"source":"enrich:decision_facts","observed_at":"2026-07-17T11:08:56.500Z"},"constraint_facets":{"min_ram_gb":16,"requires_docker":true},"decision_summary":[{"label":"Requirements","value":"Min 16 GB RAM; Requires Docker"},{"label":"Adopt for","value":"MiroFish-Offline is an offline simulation and prediction engine for multi-agent systems that uses Neo4j and Ollama framework locally."}]}}