Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks.

Lightweight Codex/Claude loop harness with strict evidence gates.

Verifiable research-report engine for DeepSeek Harness: content-addressed evidence ledger (claim-snapshot binding, tamper-evident) plus versioned sealed reports with per-claim verification verdicts and a manifest-sealed directory.

A task conductor for Claude Code that gets better the more you use it. Multi-agent orchestration with an evidence contract that BLOCKS instead of asking, gates written as hooks rather than prompts, and a retrospective that learns your repo's rules and tunes its own playbook.

Multi-engine web search and evidence synthesis for AI coding agents. Unified MCP server, Pi extension, and DeepSeek Harness bundle — free search, X/Twitter, parallel research, and TUI setup.

Native Claude Code, Codex and Pi adaptations of IdeaScientist for automatic, evidence-grounded research ideation.

Flow Agents keeps coding agents on track with evidence-backed workflows — a Kontour product that applies Flow and Veritas process discipline as a portable layer inside the agent tools you already use: Claude Code, Codex, Kiro, opencode, and pi — with fram

The operating layer for Claude Code + OpenAI Codex: persistent project memory, intent routing, safety hooks, cost telemetry, and parallel agent fleets.

Feed your agent papers and half-formed ideas — it links them into a system design you can defend. Markdown keeps the record; a visual canvas makes it readable. An Agent Skill for Claude Code & any SKILL.md-compatible agent.

Spec-driven development framework — AI agents that think before they type

The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件，为 DeepSeek、GLM 等纯文本模型外挂视觉能力，粘贴图片即得结构化 JSON 证据（OCR、版面、语义）。

Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 commands, 246 MCP tools, change-safety gates, audit evidence, zero API keys.

DSH plugin - framework upgrade safety & plugin gating: contract pre-check, rollback point, auto-rollback on failure, evidence-based auto-disable; plus a multi-source plugin market. Unofficial. | DSH 插件：框架升级安全 + 插件门控——升级前契约预检、回滚点、失败自动回滚、有确证证据才自动禁用；另带多源插件市场。非官方社区项目。

Keep intent, specifications, and verified progress portable across AI coding tools. A local live work board, append-only task evidence, explicit handoffs, and optional GitHub/Jira/Azure DevOps integrations.

Author, generate, validate and govern AI agent rules, skills, plugins and MCP configuration across 52 coding assistants. Review with verified model evidence, evaluate skills, lock and sign dependencies, and publish bundles. CLI, MCP server and Go API.

Enables comparison of supplied supplier or vendor statement open items against an accounts payable ledger, identifying missing items, amount and date discrepancies, and ambiguous repeated references with exact reference evidence.

Connects MCP-compatible clients and CI pipelines to a hosted endpoint exposing tools for SaaS revenue-leak audits, ghost-usage evaluation, EU VAT validation, B2B net-terms reconciliation, webhook signature verification and replay simulation, dispute-evidence staging/linting, and ROI calculation.

Enables AI agents to search 1,900+ exercises with video and media links, generate workouts and multi-week programs, explore evidence-rated supplements, and use developer tools for API modeling, debugging, and usage insights.

Enables agents to inspect React Native and Expo apps through React's runtime tree, identify source locations, act on elements without coordinates, and verify outcomes with assertions and runtime evidence.

Engineering decisions, change impact, documentation audits, and CI evidence for coding assistants.

Local history ingestion, storage, evidence, SDK, CLI and MCP server.

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

AI agent identity, signed credentials, delegated authority and portable governance evidence. Python core and offline verifier SDKs.

Evidence-backed UI delivery for coding agents working on existing Web products: declared criteria, criterion-bound artifacts, findings linked to declarations, and repair guidance. Evaluator review does not replace human semantic approval.