Fact-checking
Verifying claims against sources. As of 2026-11-21, 36 indexed products offer it (12 with full profiles), in 3 forms: 32 MCP servers, 2 Agent skills, 2 Plugins. 17 were published in the last 90 days, against 12 in the 90 days before. paperthin has the most GitHub stars, 78% of the total across 25 products with their own repository.
CapabilitySegment label: Thin DERScored as an opportunity
Available as
All in the directoryProfiled products grouped by product form. Within each form: own-repository products by GitHub stars, then products in a subfolder of a larger repository (they show that repository's stars), up to 10 each.
MCP servers 32 indexed · 8 profiled
Protocol-level reach: 36 of the 45 active platforms AgentSidekick tracks document support for MCP. DER Which platforms
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | CRED-1Domain credibility ratings from the CRED-1 dataset: check, batch check and search news domains | aloth | 18 | 3d ago | ||
| 2 | RogueGPTStore and retrieve controlled AI news stimuli with generation metadata for misinformation research | aloth | 8 | 14d ago | ||
| 3 | Imperal MCPMemory across sessions, a live code map, undo for every change and a fact check | imperalcloud | 5 | today | ||
| 4 | TaniloTanilo checks the premise before an AI agent acts. | TKCollective | 3 | 1mo ago | ||
| 5 | Axiom — Advanced MathExact symbolic math for LLMs: integrals, equations, matrices, and claim verification via Giac/Xcas | tufantunc | 3 | 4d ago | ||
| 6 | concordanceDeterministic claim verification with receipts across ~60 domains. No model in the loop. | narrowhighway.com | 1 | 1d ago | ||
| 7 | ProofGraph (Antigravity MCP)Evidence-first entity and knowledge graph MCP server for AI agents to verify claims. | AI-BuildInfra | 1 | 5d ago | ||
| 8 | FaultlineChecks the most important factual claims in AI output against live web sources by default. | nxtg-ai | 1 | today |
Agent skills 2 indexed · 2 profiled
Protocol-level reach: 26 of the 45 active platforms AgentSidekick tracks document support for the Agent Skills format. DER Which platforms
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | paperthinThe skillbook for recursive self-improvement (RSI). NVIDIA's latest proof, unpacked with timeless engineering. Distilled from the OpenAI harness engineering hackathon winner's zero-touch method. | LilMGenius | 1.5k | 6d ago | ||
| 2 | nemo-guardrailsNVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU. | Orchestra-Research | — | 1mo ago |
Plugins 2 indexed · 2 profiled
2 of these are Claude plugins, which Claude Code documents (protocol-level). DER
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | humanizer-skillSee why a draft sounds like AI and rewrite it in one of five voices: 55 named patterns, a 0 to 100 score, a fact check. | Aboudjem | 325 | 3d ago | ||
| 2 | swing-skillsOpen-source Claude Code skills — 6 cognitive firewalls block AI hallucination, bias & sloppy reasoning. npx skills add | TheStack-ai | 41 | 6mo ago |
Which platforms these forms can reach
All platformsProtocol-level: the platform documents support for the standard. No specific pairing has been tested.
MCP servers 32 indexed here
36 platforms document MCP support CUR.
ContinueOpenCodeClaude CodeCodexGemini CLIZedOpenHandsClineWarpgooseQwen CodeBolt (bolt.new)KiroAmazon Bedrock AgentCoreAmpApps in ChatGPT / Apps SDK (now ChatGPT Plugins)Augment CodeChatGPTClaude (claude.ai apps)Claude DesktopCursorDevinDevin Desktop (formerly Windsurf)Factory (Droid)Gemini (app)Gemini Enterprise Agent Platform (formerly Vertex AI / Vertex AI Agent Builder)GitHub CopilotGitHub Copilot cloud agent (formerly Copilot coding agent)Google AntigravityJetBrains AI AssistantJunieLovableMicrosoft Copilot StudioReplit AgentTabninev0
Agent skills 2 indexed here
26 platforms document Agent Skills support CUR.
OpenClawOpenCodeClaude CodeCodexGemini CLIOpenHandsWarpgooseBolt (bolt.new)KiroAmpApps in ChatGPT / Apps SDK (now ChatGPT Plugins)ChatGPTClaude (claude.ai apps)Claude DesktopCursorDevinDevin Desktop (formerly Windsurf)Factory (Droid)Gemini (app)GitHub CopilotGitHub Copilot cloud agent (formerly Copilot coding agent)Google AntigravityJunieReplit AgentTabnine
Platforms publishers name
| Platform | Profiled products naming it |
|---|---|
| Claude Code | 1 |
| Google Antigravity | 1 |
Integrations most often paired
Third-party services named by products with this capability, whole catalogue.
No integrations named
None of the products matched here names a tracked third-party service.
Keywords that trigger this capability
Matched as whole words, ignoring case, in a product's name, description and repository topics.
| Keyword | Products matched |
|---|---|
| fact-checking | 6 |
| fact check | 6 |
| claim verification | 18 |
| source verification | 4 |
| misinformation | 2 |
Segment statistics
Whole catalogue (36 indexed products). Calculated 2026-11-21.
Thin. Among the smallest 30% of capabilities, and launches are not outpacing the catalogue. Size is ranked against all capabilities; momentum compares launches in the last 90 days with the 90 before, relative to the catalogue’s own ratio (62 or more = faster, 38 or less = slower; under 5 dated launches it is not measured). The HHI of 0.640 means stars are spread as if across about 2 equally popular projects — highly concentrated by the common 0.15 / 0.25 thresholds. Stars measure attention, not usage or quality.
Scored as an opportunity
Score breakdownCoverage gap: Fact-checking: score 54.2 HEU, competition High, confidence Low. Only 36 indexed products match "Fact-checking", against 236 in Deep Research overall.
Limits
- Classification is by the keywords above. A product that offers this capability without using one of them is not counted; one that uses a keyword in another sense is counted wrongly. Methodology
- Platform reach is protocol-level: it says a platform documents the standard, not that any product here was tested on it. Platforms named by publishers are their own claims.
- Stars belong to repositories. Products in a subfolder of a large repository show that whole repository’s stars and are excluded from the concentration figures.
- Launch counts use each source’s publication date; for auto-discovered repositories that is the repository’s creation date.
Page data last updated .