EvoMap Evolver is a self-evolving AI agent engine built as a Node.js >=22.12 CLI daemon. It runs a genome-evolution loop: scans session memory/logs, extracts signals, selects 'Genes' (prompt/strategy patches) and 'Capsules' (validated skill bundles) from a local JSON/JSONL asset store, generates GEP-framed prompts for coding agents (Claude Code, Codex, Cursor, Gemini CLI, opencode, Kiro), executes those sessions, and records outcomes in a memory graph to adapt future selections. The system solidifies successful patterns into new reusable assets, auto-distills failure patterns and SKILL.md files into Genes/Capsules, and can open PRs or run validation sandboxes against candidate changes. It also ships an LLM proxy (Anthropic/OpenAI/Gemini/Vertex/Ollama routes with trace encryption and token-savings attribution), an ATP (Agent Transaction Protocol) marketplace for buying/completing agent tasks with auto-buyer and auto-deliver, a validation daemon for decentralized task verification, a local Web UI dashboard, and an experiment runner for A/B comparing evolution strategies. Hub synchronization (SSE event delivery, mailbox sync, OAuth device login) connects nodes to the evomap.ai network, but the system is designed to degrade gracefully into fully offline solo mode.
The Diagram of Thought (DoT) repository presents a research framework for enhancing LLM reasoning through iterative self-correction via a structured prompt. It contains no executable code or data processing pipelines, focusing instead on a conceptual model and a reusable prompt structure for guiding LLMs to construct and refine reasoning graphs. The repository includes the research paper, illustrative images, and two markdown files: a detailed README explaining the DoT framework and a prompt template for iterative reasoning with proposer, critic, and summarizer roles. As a research artifact, the repository does not ingest, transform, or analyze any datasets. Its primary value lies in proposing a novel reasoning methodology and providing a prompt that can be used with any capable LLM to implement the DoT process. The lack of code or data means there are no data engineering components to evaluate, resulting in minimal reproducibility and no reusable data assets by data engineering standards. Maintenance appears active based on a recent commit timestamp, and the codebase shows no technical drift due to the absence of dependencies or executable code. However, the repository's utility is limited to theoretical exploration and prompt engineering rather than practical data operations.