MCP servers and skills: search, filter by where they run, and compare.
Generate versioned RDF/OWL knowledge graphs from C2PA specification source files. Serve to AI agents via MCP.
PythonApache-2.0★ 3Few starsNo key
CLI tool + Claude Code skill to export Claude.ai conversations to Markdown — including artifacts, web search sources, and full message history
SkillMIT★ 2Few starsNo key
Forward videos from IM to transcript, Markdown, and your knowledge base — with raw and skill-updated outputs.
SkillMIT★ 171No key
Persistent code knowledge graph + MCP server for AI coding agents, with confidence-tagged edges and 5 durable markdown artifacts. Apache-2.0.
PythonApache-2.0★ 2Few starsNo key
AI-operable research workspace for Zotero, Obsidian, and NotebookLM. Use any two, or all three, through CLI, MCP, REST, and dashboard.
SkillMIT★ 65No key
Evidence-grounded AI research workflow for traceable claims, explicit uncertainty, causal-language checks, and reviewable JSON, Markdown, and Excel exports.
SkillMIT★ 11No key
招投标网站爬虫交付 Skill：单站独立项目、单文件 Python、CSV、字段映射、部署文档、配置说明和验收检查。
SkillMIT★ 8No key
Autonomous observation and analysis layer for AI agents — Obsidian vault indexing, scheduled reasoning cycles, and a real-time cognitive dashboard. Built on cognitive-memory.
PythonMIT★ 1Few starsNo key
Auditable MCP + cross-agent harness for autonomous and human-guided academic writing—from verified evidence to reviewed DOCX/PDF.
PythonApache-2.0★ 12No key
MCP server that compresses OCR-heavy PDFs into dense packed images so AI agents can handle long visual documents
PythonMIT★ 1Few starsNo key
MCP tools for generating, parsing, and validating FATEK WinProLadder .ldr files.
PythonMIT★ 2Few starsNo key
Deterministic stage-based pipeline for searching, screening, downloading, converting, and summarizing academic papers. CLI + MCP server.
PythonMIT★ 2Few starsNo key
Tape any API to your agent in one command. CLI factory for AI agents — prints Python CLIs, MCP servers, and skills from any OpenAPI spec, HAR file, or website.
PythonMIT★ 5No key
Evidence-first LLM-as-judge scoring for AI artifacts — papers, PRs, prompts, cold emails: synthesizes a rubric, collects quoted-evidence citations, scores only against that evidence, and hedges on thi
SkillApache-2.0★ 2Few starsNo key
PDF circuit schematic to evidence-preserving SchematicIR JSON converter and MCP server
PythonMIT★ 3Few starsNo key
LibreOffice headless automation via FastMCP — Writer/Calc/Impress convert, ODT merge, PDF combine, folder watch. For Cursor / Claude Desktop.
PythonMIT★ 5No key
Email access for AI agents across files, Gmail, IMAP, MCP, and provider-backed sending.
PythonMITFew starsNo key
Multi-backend, agent-friendly forecasting for publishable charts, cards, markdown, and JSON.
PythonMIT★ 3Few starsNo key
MCP server exposing a markdown vault as an agent memory substrate — vault is truth, DuckDB index is disposable, writes are constrained verbs
PythonMIT★ 3Few starsNo key
Shareable links for what your AI agent makes. vitrine is a small, self-hosted MCP server. Your agent publishes an HTML report, a chart, a PDF or a folder of files, and gets back a link that opens in a
PythonMIT★ 1Few starsNo key
Red-team harness for tool-using AI agents. Injection payloads planted in files, web pages, emails and command output; tripwire-scored ASR. Zero dependencies, stdlib only.
PythonMIT★ 2Few starsNo key
BGI tries to group code based on what the code actually does (its behavior), not just which file imports what.
PythonApache-2.0★ 4Few starsNo key
AST JAX-aware linter for JAX-specific concerns and doc quality - includes CLI, LSP, and MCP
PythonMIT★ 4Few starsNo key
Who stands behind it
