Pinned Loading

1. prism prism Public

   Reliability primitives for multi-agent AI — VotingMesh consensus, Sentinel safety pipeline, Aegis exchange compliance, checkpoint/replay. Rust + Tokio + PyO3 Python bindings. 95 tests.

   Rust 1 1

2. bastion bastion Public

   Safety kernel for agentic AI — multi-model consensus, deterministic verification, SHA-256 audit trails, checkpoint/rollback, self-healing. Rust + Tokio.

   Rust 1 1

3. flux-swarm-builder flux-swarm-builder Public

   Build a multi-agent AI team from markdown files. Runs locally on your GPU. Zero cloud dependency.

   Python 1 1

4. agentbench agentbench Public

   Framework-agnostic CLI tool for benchmarking AI agents across standardized tasks

   TypeScript 1

5. math-swarm math-swarm Public

   Zero-hallucination computation engine for LLMs. 1,079 tests, 12 categories, 100% accuracy. Benchmarked: 3B (55%) vs 7B (77%) vs 32B (93%) vs Math Swarm (100%). 15 clinical formulas with guideline-b…

   Python 3 2

6. knowledge-graph-reasoning knowledge-graph-reasoning Public

   Agent Skill for Claude: Build, query, validate, and reason over knowledge graphs. Adversarial fact validation, deterministic reasoning, JSON-LD schema.

   Python 1 1