Benchmark for tracking model capability after release.
Quick read
Latest capture 2026-10-01 04:01
1 path
Agent instructions and tool configuration found in this repository.
Claude Code
1 observed capture since 2026-10-01. Observed captures are shown by default.
Stars from first capture 0
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
LiveBench: A Challenging, Contamination-Free LLM Benchmark
Cross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited neuroscience mechanisms, local-first SQLite/PostgreSQL, hybrid retrieval, decay-based consolidation, and reproducible benchmarks. Claude adds optional automatic lifecycle hooks.
LLM-as-a-Verifier is a general-purpose framework that provides fine-grained feedback for any agent without requiring additional training. It achieves SOTA performance across coding, robotics, and medical agentic benchmarks.
Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded in 2025-2026 research on model laziness, underthinking and premature completion.
Compiles a demonstrated GUI task into a program that reports VERIFIED only if an independent check agrees. pip install openadapt; openadapt flow tutorial. Compiler lives in openadapt-flow.
Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.
