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.

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.

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.

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.