PrismShadow

Pinned Loading

1. penguin-harness penguin-harness Public

   🐧 Harness for RSI. Let AI Build AI

   TypeScript 1.4k 140

2. GDPevo GDPevo Public

   A Benchmark for Evaluating Agent Self-Evolution on Real Business Tasks

   Python 55 2

3. agenthub agenthub Public

   AgentHub SDK is the unified and transparent multi-LLM SDK for building reliable Agent Apps. (GPT-5.5/Claude 5/Gemini 3.6)

   Python 105 11

4. context9 context9 Public

   Your personal knowledge MCP engine. Up-to-date, local-first, low-hallucination.

   TypeScript 30 2

5. agentic-retrieval-bench agentic-retrieval-bench Public

   A reproducible benchmark for LLM-augmented retrieval on Multi-CPR and LexRAG.

   Python 2

6. agent-provider-verifier agent-provider-verifier Public

   Agent Vendor Verifier is a tool for validating the fidelity and reliability of tool-calling LLMs across different vendors.

   Python 4