Developer Tools / AI / ML Infrastructure
Experimental page-aware Metal runtime and reproducibility harness for running oversized sparse mixture-of-experts models on Apple Silicon. The repo documents GPT-OSS 120B support, performance results on 64 GiB and 16 GiB machines, and the runtime/harness structure.
The snapshot shows a real, AI-adjacent developer project with a specific technical purpose: page-aware inference for oversized MoE models on Apple Silicon. The README gives enough evidence for a useful listing, including target model details, benchmark-style results, and a map of the runtime, harness, and scripts.
The page reads as research documentation rather than a ready-to-use product, and the snapshot does not show install steps, a quickstart, API surface, or a simple usage example. It also does not make the maintenance status or broader model support easy to judge from the visible text.
Last evaluated 33 days ago. Current rank #1322. Down 2 spots in the rankings.
CodeGraph is a local code knowledge graph for AI coding agents like Claude Code, Cursor, Codex, OpenCode, and Hermes Agent. It aims to cut token use, tool calls, and runtime by letting agents query pre-indexed code structure instead of scanning files repeatedly.
Mercemur is a store automation platform with three interfaces: a REST API, an MCP server for AI agents, and a CLI for editing storefronts as files. The docs show authentication, scopes, rate limits, error handling, pagination, idempotency, and a large API surface for catalogue, orders, customers, pricing, and money.
A zero-dependency C++23 CLI and MCP server that gives coding agents a ranked map of a repository, including call context, blast radius, and tests to run.
Traccia is an AI agent observability and governance platform with OpenTelemetry-native tracing, runtime policy enforcement, prompt registry, evals, cost attribution, and compliance evidence export.
