agentic-research
Local research agent that verifies its own answers. Runs on Gemma 3 4B + Ollama, $0/query.
Open the source (opens github.com) https://github.com/theaisingularity/agentic-research-engine-oss
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
- Needs credentials: OPENAI_API_KEY. Use a key with the least access you can.
What it is
MCP servers from io.github.TheAiSingularity.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
pypi package (stdio)
agentic-research-engine@0.1.3
From the server's entry in the official MCP Registry
Settings it asks for
OPENAI_BASE_URL· Any OpenAI-compatible endpoint. Default: OpenAI cloud. Use http://localhost:11434/v1 for Ollama.OPENAI_API_KEYsecret · API key for the endpoint above. Use 'ollama' as a sentinel value when running locally against Ollama.MODEL_SYNTHESIZER· Model identifier used for the synthesize node. Defaults to 'gpt-5-mini'; set to 'gemma3:4b' for Mac-local Ollama.MODEL_PLANNER· Model for the plan / classify / critic / compress / verify nodes. Defaults to 'gpt-5-nano'.EMBED_MODEL· Embedding model identifier (for retrieval + memory). Default 'text-embedding-3-small'; use 'nomic-embed-text' on Ollama.SEARXNG_URL· Base URL of the SearXNG meta-search instance. Default http://localhost:8888.LOCAL_CORPUS_PATH· Path to an index directory built via scripts/index_corpus.py. When set, local corpus hits augment web search.ENABLE_RERANK· Set to '1' to enable the BAAI/bge-reranker-v2-m3 cross-encoder rerank stage. First run downloads ~560MB.ENABLE_FETCH· Set to '0' to skip the trafilatura full-page fetch stage. Default '1'.
Related
-
Picked by Agents Research Network
MCP serversJoin voluntary research studies and record how AI assistants choose local businesses.
-
Secant Agent Research Pack
MCP serversPaid MCP web research for agents: search, extraction, citations, and x402 payment discovery.
-
ExMachina AI — agent research rooms
MCP serversAI agents collaborate on open biomedical problems, citing sources that are machine-checked.
-
mache
MCP serversIDE-style navigation for structured data — code, JSON, YAML. Jump to definitions, find callers, follow references. Available as an MCP server or a mounted folder.
git clone https://github.com/agentic-research/mache.git -
hyperresearch
MCP serversConvert Claude Code or Codex into the most intelligent Deep Research Agent. Collect, search, and synthesize web research into a persistent, searchable wiki that builds on itself. Hosted API + MCP: hyperresearch.ai
git clone https://github.com/jordan-gibbs/hyperresearch.git -
flexreport-mcp
MCP serversMCP server for real-time equity research: real-time market events, 13F ownership, earnings transcripts, fundamentals, estimates & insider filings on 2,900+ companies for Claude and other AI agents.
git clone https://github.com/cbecks1212/flexreport-mcp.git