Research-grade investment decision engine for AI agents: isolated multi-agent committee, auditable verdicts, backtests with lookahead protection, published negative results

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default, fully auditable from the session log (approval/asked -> autoReview/verdict -> approval/decided).

Verifiable research-report engine for DeepSeek Harness: content-addressed evidence ledger (claim-snapshot binding, tamper-evident) plus versioned sealed reports with per-claim verification verdicts and a manifest-sealed directory.

BrandDocs is a set of agent skills that learn your existing Word, PowerPoint and Excel templates and generate new on-brand documents from them. Unlike generic AI document generators, it preserves brand, structure, styles and formulas by construction. Built for Claude Code, Codex and compatible AI agents.

Run one project across your own Windows and macOS machines from a single DeepSeek account, through 11 w2m_* tools. Four coordination modes (replicate, split, broadcast, pipeline) and six aggregate verdicts (consistent, divergent, divergent-platform, faile

Enables AI assistants to perform read-only checks of sky positions against public astronomy archives, returning compact JSON verdicts and evidence for known transients, variables, TESS objects, asteroids, and other objects, plus observation planning and image links.

Local-first visual regression for AI agents: verdicts, diff images, explain_snapshot. No API key.

Enables agents to verify whether a quoted passage appears word for word in a cited URL, DOI, or PubMed source, returning a verdict, similarity score, and character span so quotations can be validated before use.

Check any agent skill or MCP server's security verdict before your agent installs it. Sandbox-based 0-100 verdicts (Verified, Caution, Blocked). Free, read-only, no account.

Vendor-neutral control-plane contract for coding agents: a normalized ToolCallEvent/Verdict schema with per-agent adapters (Claude Code, Codex, Amp, Gemini CLI) and a conformance suite.

Static capability disclosure for DeepSeek Harness plugins: capabilities, injected prompts, install scripts, and provenance, each with file:line evidence. Facts, not a safety verdict.

Solana swap safety for agents: free token screen, $0.01 swap verdict, $0.02 built swap via x402.

Quant research skills for coding agents on 0xArchive data. Reverse engineer any trader, test any idea: a deterministic Rust backtester, a trial ledger, a sealed holdout and a verdict you can rerun. Plus live market data for Hyperliquid and Lighter.

Author rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.

Memory for AI agents that knows what is still true. Typed bi-temporal facts, EU-hosted.

Multi-agent mathematical problem-solving & verification frameworks for DeepSeek Harness — FOUR agent presets in one install: vibe-math-v2 (probability-driven, classic: qs.json + Propos knowledge base + explorer→solver→review/debate verdict), vibe-math-v3

Guardrails for LLM output: pass / fail / review verdicts and one recommended action. Hosted or npm.

Devil's advocate for coding agents. Stress-tests plans, architecture and decisions with a steel-man, an assumption audit and a pre-mortem, then gives severity-rated findings and a verdict. Works in Claude Code, Codex, Cursor, Gemini CLI, Copilot and 12 more.

The deterministic agent-integrity gate. One ruleset, evaluated on the actual diff/commands as a verdict, enforced everywhere a change can be made.

Shared project memory for people and AI agents: workspaces, documents, ERD, diagrams and boards.

Open-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI agent access to profiles, companies, jobs, and messages.

Headless MCP server for Metabase: API-key auth (no OAuth), stdio or HTTP, 178 tools with toolsets, works on every Metabase tier

Deterministic pre-execution audit for trading agents. PASS/WAIT/FAIL, reproducible verdict_hash.

Check if a US stock is halal (Sharia-compliant), with the dates its verdict changed.