Critical thinking platform for decision analysis, proposal review, debate preparation, and due diligence. Three agents (advocate, adversary, judge) over a grounded argument graph, with a live transcript UI, appeal review, and 10 reasoning traditions.
★not rated 7
changed yesterdayA
tokens not measured
originalMIT
A weekly sweep for open product roles that match you — and remembers what it already showed you. Standalone: no pipeline, no tracker, no setup beyond a CV or three questions.
★not rated 7 9d agoA
tokens not measured
originalMIT
Semantic (vector) and full-text (keyword) search across indexed corpora via the arc CLI. Dual-indexes PDFs, markdown, and source code into Qdrant + MeiliSearch with AST-aware chunking, frontmatter, and git metadata. Use full-text for exact symbols/phrases and semantic for conceptual queries — both are first-class.…
★not rated 7 9d agoA
tokens not measured
originalMIT
Strategic technical advisor with two modes. REPO MODE (gpt-5.2) explores your codebase to find gaps and review code. WEB MODE (5.2 Thinking / GPT-5.2-pro) researches external info like best practices and library comparisons. Run both in parallel to compare your implementation against current standards.
★not rated 7 2mo agoA
tokens not measured
originalMIT
Scientific Research Reasoning Engine for evaluating experimental and empirical claims — auditing ML training runs, ablations, and sweeps; reviewing papers; checking reproducibility; and producing structured research reports. Optional Weights & Biases integration via the experiment-audit-mcp server.
★not rated 7▲
+3 9d agoA
tokens not measured
originalMIT
Persistent, private memory for Claude Code — every session archived into a local, searchable SQLite database. What's said under the rose stays under the rose.
★not rated 6▲
+1 3d agoA
tokens not measured
originalMIT
Compiler-exact code search for .NET, for Claude Code and Codex - find references, callers and change impact across C#, VB, Razor Pages, MVC views and Blazor components. Built on Roslyn, so answers come from the compiler rather than pattern matching, and Razor and Blazor are indexed rather than skipped. Deterministic…
★not rated 6 yesterdayA
tokens not measured
originalMIT
Drillr financial MCP for AI agents — four-market financial data, company-filing and semantic news search, plus 24 alt-data categories. One HTTP MCP server exposing 9 tools.
★not rated 6 7d agoA
tokens not measured
originalMIT
YouTube video intelligence via Gemini: channel scanning, rich multimodal transcripts with on-screen content, concept taxonomy, hybrid search, and Bosnian/Croatian/Serbian subtitle translation. Three skills: video-intel (ingest/curate, runs in the plugin repo), video-intel-search (read-only, globally installable)…
★not rated 6
changed yesterdayA
tokens not measured
Search EU legislation, CJEU case law, and treaties; traverse the CELLAR relationship graph; resolve EuroVoc concepts via MCP. STDIO or Streamable HTTP.
★not rated 6
changed todayA
tokens not measured
originalApache-2.0
METASCI — a personal Claude Code skill collection spanning academic research (knowledge/logic/vocabulary extraction, writing, rewriting, multi-reviewer proofreading, agentic research) and dialogue personas (Virgil, Beatrice, Socrates, Picasso, Feynman digest). Supports AI collaboration based on Gemini CLI.
AI-assisted computational research with license-aware MCP-first Wolfram execution, wiki knowledge base, LaTeX/Typst paper scaffolding, Wolfram paclet development, symbol-page documentation bundled and publicly deployed on publish, dual-engine Markdown-to-notebook conversion that auto-detects a pinned rich converter…
★not rated 6 14d agoA
tokens not measured
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: