{
  "slug": "io-github-theaisingularity-agentic-research",
  "name": "io.github.TheAiSingularity/agentic-research",
  "title": "agentic-research",
  "description": "Local research agent that verifies its own answers. Runs on Gemma 3 4B + Ollama, $0/query.",
  "version": "0.1.3",
  "publishedAt": "2026-04-20T21:47:07.536306Z",
  "updatedAt": "2026-04-20T21:47:07.536306Z",
  "repoUrl": "https://github.com/TheAiSingularity/agentic-research-engine-oss",
  "websiteUrl": null,
  "namespace": {
    "type": "github",
    "owner": "TheAiSingularity"
  },
  "kind": "local",
  "packages": [
    {
      "registryType": "pypi",
      "identifier": "agentic-research-engine",
      "version": "0.1.3",
      "transport": "stdio",
      "runtimeHint": "agentic-research-mcp"
    }
  ],
  "remotes": [],
  "envVars": [
    {
      "name": "OPENAI_BASE_URL",
      "isSecret": false,
      "isRequired": false,
      "description": "Any OpenAI-compatible endpoint. Default: OpenAI cloud. Use http://localhost:11434/v1 for Ollama."
    },
    {
      "name": "OPENAI_API_KEY",
      "isSecret": true,
      "isRequired": false,
      "description": "API key for the endpoint above. Use 'ollama' as a sentinel value when running locally against Ollama."
    },
    {
      "name": "MODEL_SYNTHESIZER",
      "isSecret": false,
      "isRequired": false,
      "description": "Model identifier used for the synthesize node. Defaults to 'gpt-5-mini'; set to 'gemma3:4b' for Mac-local Ollama."
    },
    {
      "name": "MODEL_PLANNER",
      "isSecret": false,
      "isRequired": false,
      "description": "Model for the plan / classify / critic / compress / verify nodes. Defaults to 'gpt-5-nano'."
    },
    {
      "name": "EMBED_MODEL",
      "isSecret": false,
      "isRequired": false,
      "description": "Embedding model identifier (for retrieval + memory). Default 'text-embedding-3-small'; use 'nomic-embed-text' on Ollama."
    },
    {
      "name": "SEARXNG_URL",
      "isSecret": false,
      "isRequired": false,
      "description": "Base URL of the SearXNG meta-search instance. Default http://localhost:8888."
    },
    {
      "name": "LOCAL_CORPUS_PATH",
      "isSecret": false,
      "isRequired": false,
      "description": "Path to an index directory built via scripts/index_corpus.py. When set, local corpus hits augment web search."
    },
    {
      "name": "ENABLE_RERANK",
      "isSecret": false,
      "isRequired": false,
      "description": "Set to '1' to enable the BAAI/bge-reranker-v2-m3 cross-encoder rerank stage. First run downloads ~560MB."
    },
    {
      "name": "ENABLE_FETCH",
      "isSecret": false,
      "isRequired": false,
      "description": "Set to '0' to skip the trafilatura full-page fetch stage. Default '1'."
    }
  ],
  "category": "ai-media",
  "subcategory": "llm",
  "company": "",
  "categoryAuto": true,
  "checks": [
    {
      "id": "source-linked",
      "label": "Source repository linked",
      "result": "pass",
      "detail": "https://github.com/TheAiSingularity/agentic-research-engine-oss"
    },
    {
      "id": "version-pinned",
      "label": "Version pinned",
      "result": "pass",
      "detail": "Every package has an explicit version"
    },
    {
      "id": "secrets-requested",
      "label": "Secrets requested",
      "result": "info",
      "detail": "Asks for 1 secret: OPENAI_API_KEY"
    },
    {
      "id": "known-registry",
      "label": "Known package registry",
      "result": "pass",
      "detail": "All packages come from npm, PyPI, OCI, NuGet or MCPB"
    },
    {
      "id": "namespace",
      "label": "Namespace ownership",
      "result": "info",
      "detail": "Name verified via GitHub account TheAiSingularity"
    },
    {
      "id": "meta-text",
      "label": "Registry text aimed at the AI",
      "result": "pass",
      "detail": "Description and settings contain no hidden characters or instructions to the AI"
    },
    {
      "id": "install-scripts",
      "label": "Install scripts",
      "result": "pass",
      "detail": "agentic-research-engine 0.1.3 has no setup.py; nothing runs at install"
    },
    {
      "id": "code-flags",
      "label": "Code red flags",
      "result": "pass",
      "detail": "Read 68 files in agentic-research-engine 0.1.3: no obfuscation, encoded execution, credential reads or data-collection endpoints found"
    },
    {
      "id": "ai-text",
      "label": "Text aimed at the AI",
      "result": "pass",
      "detail": "No hidden characters or instructions to the AI in 68 files, including comments and the README"
    }
  ],
  "scannedAt": "2026-10-29",
  "level": "Scanned",
  "install": [
    {
      "label": "Claude Desktop (pypi)",
      "kind": "claude_desktop_json",
      "text": "{\n  \"mcpServers\": {\n    \"agentic-research\": {\n      \"command\": \"uvx\",\n      \"args\": [\n        \"agentic-research-engine==0.1.3\"\n      ]\n    }\n  }\n}"
    }
  ],
  "curated": true,
  "stars": 2,
  "archived": false,
  "pushedAt": "2026-04-21T17:43:02Z",
  "health": {
    "score": 40,
    "parts": {
      "popularity": 0.19340086226772202,
      "activity": 0.18,
      "issues": null,
      "security": 1
    },
    "fail": 0,
    "warn": 0,
    "raw": {
      "stars": 2,
      "forks": 1,
      "downloads": 28,
      "hn": null,
      "issuesOpen": 1,
      "issuesClosed": 0,
      "prsMerged": 0,
      "commits90": 0,
      "release": "2026-04-20T21:43:45Z",
      "pushed": "2026-04-21T17:43:02Z",
      "growth": null,
      "growthDays": null,
      "archived": false
    },
    "at": "2026-10-31T07:42:38.200Z"
  }
}