v0.6.2 · MIT
Trace Compare & Live Maze for DeepSeek Harness: visualize agent exploration (main path, detours, backtracks) from session logs or live sessions
— · no license
Structural memory for AI coding agents. Bi-temporal graph, MCP-native, zero LLM calls. Cursor · Claude Code · Codex · DeepSeek Harness · Hermes · VS Code · Windsurf.
v1.7.7 · MIT
Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.
v1.0.0 · MIT
Evidence-first deep reading for AI agents — trace claims, evidence, confidence and knowledge maps across articles, books and PDFs.
v0.5.0 · MIT
深迹 DeepTrace — Your Agent, in numbers. DSH 插件:从会话事件日志生成日报/周报/月报/年报/自定义区间,确定性洞察与协作复盘,只读、不改写历史。
v0.1.0 · MIT
Open-source macOS record-and-replay workflow recorder for computer use agents. Captures mouse, keyboard, and UI events as structured traces so agents can learn, replay, and automate real desktop tasks.
— · Apache-2.0
Token Bank — the local LLM gateway that sits between your AI agents and every provider. Know where tokens go · Spend less with smart routing to Ollama, Groq, GitHub Models · Earn by sharing idle quota on a community P2P network. One-click onboarding for Cursor, Claude Code, Codex CLI, Gemini CLI — no agent changes. Full trace, seamless model swap
— · MIT
Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.