I built a research agent that tries not to sound more confident than it should

A developer built ResearchAgent, an open-source research agent that runs explicit stages—planning, evidence gathering, verification, and synthesis—rather than a single reasoning pass, and assigns a confidence score based on a checklist of source count, consistency, recency, and whether original constraints were met. Low-authority sources are filtered out early to keep them from inflating the final score, and the agent supports fully local execution via DuckDuckGo and Ollama plus optional human approval gates before planning and synthesis. The developer says confidence calibration is still being improved, with claim-level confidence planned next.

Most research agents I’ve encountered share a rather annoying tendency: they hallucinate a citation or exaggerate the credibility of a weak source and still present the answer with complete confidence. Consequently, I often find myself spending a significant portion of my time “using” these agents simply to manually verify whether the sources genuinely support the claims they made. I got tired of that, so I built ResearchAgent. It’s a focused open-source agent designed for technical and architectural research inquiries. You provide it with a specific task or question to address. “Compare the top 3 open-source vector databases for a startup with 10k QPS and tight cost constraints” …and it returns a structured answer with: Design choices that mattered Instead of one big reasoning blob, it runs through explicit stages: The confidence score is not merely a subjective assessment. The synthesizer meticulously evaluates a concise checklist that encompasses the number of sources, the consistency between them, their recency, and whether the original constraints were effectively met. Consequently, sources of low authority or insufficient quality are filtered out early, minimizing the likelihood of them influencing the final score. It also supports full local execution DuckDuckGo + Ollama if you don’t want to use paid APIs, and has optional human approval gates before planning and synthesis. Why the stages help At first the extra structure feels like friction. But the first time something goes wrong, being able to look at the plan, the raw evidence, and the verification scores separately is much better than staring at a wall of chain-of-thought and guessing where it failed. Try it Repo is here: https://github.com/spidervirus/ResearchAgent https://github.com/spidervirus/ResearchAgent It includes progressive examples from a plain LLM call all the way to the full agent and a short tutorial if you want to see how each piece works. I’m still improving the confidence calibration and want to move toward claim-level confidence later. Feedback from people who actually use research agents is very welcome.