Evidence-first reading for AI agents — turn articles, books and PDFs into traceable claims, evidence, source locations and knowledge maps.

Protocol-layer harness for DeepSeek: Python witness stack — posterior verification that keeps the protocol honest. dsh doctor --node probes included.

Notes for you, Memory for your agents. / 内置 Deepseek harness Agent / 适用 办公 & 写作 & Coding

Causal memory layer for AI agents — MCP server that records decision→outcome relationships. Survives compaction.

One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.

Reverse engineer anything with agents, from app behavior down to native binaries.

Open-source desktop AI agent workspace with one-click Claude Code, Codex, OpenClaw, Hermes Agent setup and custom LLM model routing.

Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks.

J-Space Cognition Suite V3.7 - AI cognitive-enhancement Skills based on Anthropic's J-space global workspace research. | 哔哩哔哩：Tiger380 (UID 3494375382321675) — https://space.bilibili.com/3494375382321675

Distilly — Distill how they think into reusable Skills for any Agent or Bot. Formerly Colleague Skill（原同事 Skill）.

📖 Cross-agent research paper toolkit for Claude Code, Codex, OpenCode, and DeepSeek Harness—quick summaries, deep study materials, code demos, and a local web viewer.

900+ pure-markdown skills for autonomous AI research, organized as 9 freely-composable packages over a 4-layer hierarchy (Campaign → Strategy → Tactic → SOP). Non-linear orchestration with backtracking, 6 MCP integrations. The AI is the researcher — you set the direction.