Developer Tools / Code Assistant
A blog post describing a small reinforcement-learning agent trained with PPO to play and beat a Pokelike/Pokerogue-style game, including the input representation, model architecture, and training approach.
The page clearly describes an AI agent project with enough technical detail to be useful in a public directory listing. It explains the game environment, the state/action design, the 1386-dimensional input vector, the shared trunk with policy/value heads, and the training approach with PPO. The post also includes the outcome of the experiment and concrete modeling choices that affected performance.
This is a write-up of a project, not a product page or repo, so it does not show a downloadable artifact, code link, setup steps, or how others can run the agent. It also leaves out training data details, code availability, and whether the project is maintained beyond this post.
Last evaluated 97 days ago. Current rank #1900. Down 1 spot 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.
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.
Single-binary CLI that builds an AI agent knowledge base from git repos, Claude Code/Codex sessions, and saved links. It generates a portable markdown wiki, runs on cron, supports local Ollama mode, and exposes the result for agents via CLAUDE.md/AGENTS.md and MCP.
