A sample ChatGPT API Gateway. A robust interface for interacting with third-party APIs using FastAPI
Repositories
ruvnet repositories
Cognitum Claude Code plugins (MCP server registration for cognitum.one/mcpSse)
A debugging and control layer for embodied graph systems — cut the wiring, measure the fracture, ask what structure made the failure inevitable.
An app that video streams console output to YouTube Live. Uses Python, Google/YouTube API, and Replit service.
This Contextual Retrieval System enhances the accuracy and relevance of information retrieval by incorporating context into the search process. It leverages OpenAI's GPT-4 model, LlamaIndex, FastAPI, LiteLLM, and uses Supabase for both vector storage and document storage and management.
CVE-bench — conformant reproduce-and-fix security benchmark from public CVEs + OSS fix-PRs/tests. Apply-patch -> run the security test (FAIL->PASS). Cost-Pareto leaderboard, PR-based submissions, nightly CI.
Decentralized Autonomous Applications (DAAs). Building the Future with Self-Managing Applications.
A curated list of Dapps featured in the Valora wallet.
Git-based Visual CMS for Deno, </> htmx and Tailwind apps. Deploy on any Deno-compatible host.
Visual planning and context control for shipping big apps with AI coding. Build from scratch or map existing repos. Dossier maps user workflows, sets agent context per feature, builds, tests and ships from one interface.
DreamFactory API Generation Platform - API Wrapper for SQL Server, Snowflake, MySQL, and more!
Verbatim mirror of the git.drupal.org repository for Drupal core. Please see the https://github.com/drupal/drupal#contributing. PRs are not accepted on GitHub.
DS.js (Declarative Self‑learning JavaScript
A dyamic MCP Registry using Cookiecutter templates
What if you could predict every election at an individual level for the entire world in real time?
Open sourced predictions, execution logs, trajectories, and results from model inference + evaluation runs on the SWE-bench task.
FACT – Fast Augmented Context Tools: FACT is a lean retrieval pattern that skips vector search. We cache every static token inside Claude Sonnet‑4 and fetch live facts only through authenticated tools hosted on Arcade.dev. The result is deterministic answers, fresh data, and sub‑100 ms latency.