Stars
Open-source AI teammates in Slack, Teams, Discord, Telegram and Mattermost. Self-host it, with any agent harness and any model.
Find the pill that's treating another pill. Three AI agents on a FalkorDB graph detect prescribing cascades and hand a clinician one question. Synthetic data, decision support only. Graph Hacks 2026.
24 hours starts the moment you know. The EU Cyber Resilience Act Article 14 reporting clock as a GitHub Action: SBOM, actively exploited vulnerability detection (CISA KEV), ENISA drafts.
Who makes Starlink dodge. Open daily screen of every close approach between Starlink and the rest of low Earth orbit, attributed, signed and verifiable. SGP4 on public data.
Empirically calibrated false-positive bound for one-sided checksum ABFT on bfloat16 GEMM, where the classical τ = Ku threshold is undefined. Catches 76% of exponent-bit flips against a pre-register…
When the grid goes dark, the porch lights stay on. An offline-first emergency network for neighbourhoods.
Preregistered, bias-corrected test of TypeSafe Jev's calibration under human disagreement (ChaosNLI, 100 labels per item)
Canadian payroll deduction calculation. Effective-date versioned. Shows its work.
Reads local Claude Code, Codex, and Cursor history and ranks chores you keep paying an agent to redo. Local only. https://play.modiqo.ai/gautamtalksdev/groundhog
Tool-integrity pinning for MCP. Pin what your agent approved; block it when it changes.
An access governance agent. Finds every grant your people and your AI agents still hold, waits for human approval, and writes a verifiable audit trail. Built on TrueForge.
Public append-only log for AI evaluation pre-registration. Seal the metric, threshold and dataset digest before you run; bind results afterwards. The log assigns the attempt number, not the claimant.
A tool that tried to prove vulnerabilities were absent from shipped binaries. It does not work. Published in full: paper, corpus, and the audit trail.
Verified self-healing web scrapers. Every AI repair is tested against golden fixtures before it ships, and every row carries a provenance receipt with its full heal lineage. Built on Bright Data Sc…
Creator site for Gautam Talks. Hand written, zero frameworks, self updating from YouTube, with a 3D room hidden inside.
The open-source agent harness - the runtime layer that turns an LLM into a working agent.
Official Bright Data CLI - scrape, search, and extract structured web data directly from your terminal.
A super fast Graph Database uses GraphBLAS under the hood for its sparse adjacency matrix graph representation. Our goal is to provide the best Knowledge Graph for LLM (GraphRAG).
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free
The execution layer for AI agents. Act across more of your systems with precise controls: safer, faster and more efficient than MCP tools and gateways.
Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.
Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator



