TheAiSingularity/agentic-research-engine-oss
Plugin Claude Code
Local-first research agents from TheAiSingularity. Currently ships the agentic-research plugin (8-node pipeline with CoVe verification, 6 domain presets, bring-your-own-docs).
TheAiSingularity/agentic-research-engine-oss
Plugin Claude Code
Research agent that verifies its own answers with full source citations, optional local corpus, and zero cloud dependency. Runs on Gemma 3 4B via Ollama or any OpenAI-compatible endpoint. Every LLM call, source, and verification decision is visible. No telemetry.
TheAiSingularity/agentic-research-engine-oss
Skill Claude CodeCodex
Stress-test any answer against its evidence. Extracts every factual claim, checks each against the provided sources, and marks claims as VERIFIED / UNVERIFIED / CONTRADICTED. Use before trusting a research answer, summary, or analysis — especially on multi-hop topics where one bad link corrupts the whole argument.
TheAiSingularity/agentic-research-engine-oss
MCP server Claude CodeCodexCursor
The best $0 research agent that runs on a laptop — local-first, CoVe-verified, with CLI / TUI / Web GUI + MCP server + Claude plugin. Runs locally from the agentic-research-engine Python package. Needs 9 environment variables to run.