AI made building cheap. It didn't make deciding cheap. Mycelium is a Claude Code harness that makes your agent run discovery and weigh evidence before it writes code. It earns the right to start. Built for software, courses, AI tools, and services.

German AI Text Humanizer for Claude Code & Codex. Audits 72 German AI-writing patterns using deterministic linters and evidence-safe rewrites. No fact-bending, no bypassing tricks.

Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.

Local-first AI project orchestration workbench and CLI plugin for DeepSeek Harness: approval-gated planning, Git worktrees, task execution, Issues, and auditable evidence.

A minimal, evidence-gated harness for Codex and Claude Code: reuse what works, add only what is missing, verify before evolving.

Run budgeted reports and datasets with Hound, Webhound's DeepSeek V4 Pro + GPT-5.4 research harness, and return inspectable cited evidence.

Give text-only DeepSeek Harness agents video understanding: scene-aware frame sampling + VLM + optional ASR transcript fused into timeline evidence. / 给纯文本模型的视频理解插件（场景感知抽帧 + VLM + 可选语音转录）

AI agent 通用任务治理框架：对齐目标与事实，规划和调度能力，守住授权与风险边界，治理任务执行到真实验收与交付。Governance framework for evidence-driven planning, orchestration, and verified delivery.

MindsEye: model-driven vision tools, structured evidence, and exact cache for DeepSeek Harness

The AI-coding operations layer that makes "done" require evidence — persistent memory, evidence-gated completion checks, and clean handoffs for any AI agent (Claude Code, Codex, Cursor). State lives as plain files in your repo. CLI + MCP, 0 runtime depend

An intent-calibrated DSH discussion mode that prevents complex conversations from drifting and turns them into evidence-based next steps.

CertScore website risk-signal tools for scans, findings, evidence, and latest-domain lookups.

Evidence-backed TS/JS repo structure lens for Claude Code

Agent memory with no API key, no LLM, and no embedding provider. Serves MCP over stdio against a local SQLite store, or Cloudflare Workers + D1. Drop-in for @modelcontextprotocol/server-memory; every memory keeps its source, its scope, and the evidence th

Enables AI agents to run durable, isolated, and observable browser automation tasks via Playwright, with persistent profiles, recovery, evidence capture, and unattended execution for long-running web workflows.

Enables coding agents to query a local, versioned knowledge graph of a software project, retrieving overviews, context packs, evidence, and explanations to make informed changes.

Enables AI agents to perform read-only static analysis of Node.js backend projects, detecting database query anti-patterns, async bottlenecks, connection pooling mistakes, and dependency hygiene issues while returning structured evidence-backed findings.

DeepSeek V4 × J-Space capability realization report — benchmark evidence that J-Space reduces capability-realization loss on DeepSeek V4.

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

穷理证澈 Academic Research Skills: Plan the work, search the literature, draft and review manuscripts, run research code, and keep the evidence trail in one place.

Provides a local SQLite-backed code context knowledge base with MCP tools for storing and querying code facts, call graphs, semantic info, evidence, and business mappings, plus versioned snapshot publishing and incremental sync.

Enables agents to read and resolve layered feedback, propose and make decisions with evidence, and access trial ledgers and judgment views for experiment-driven work.

Read AFMR failure modes and discover scoped attestation and lift-evidence contracts.

Verify Seal AI decision receipts: signed evidence anyone can check, no account needed.