Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings
@renezander030
renezander030
Follow

René Zander renezander030

Enterprise AI Architect | Production-Ready AI Agents for CRM & ERP

Highlights

  • Pro

Block or report renezander030

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
renezander030 /README.md

banner

Hey, I'm René

I build automation CLIs and AI-agent tooling — sharp single-purpose command-line tools, plus the production patterns (approval gates, schema validation, audit logs) that let agents touch real systems safely.

If you script things, run agents, or want CLIs that do one job well with JSON output you can pipe — this profile is for you. Follow for new CLIs and production-AI patterns as they ship.

Follow capcut-cli stars Profile views

Start here

  • capcut-cli — CLI to edit CapCut / JianYing drafts (subtitles, timing, speed, templates, cut long-form → shorts). No API; reads draft_content.json directly
  • draftcat — governed AI pipelines for service businesses: deterministic-first, operator-approved, single Go binary (MIT)
  • agentic-task-system — your task manager is the best agent memory you're not using: hybrid retrieval (RRF) over TickTick / Obsidian
  • agent-approval-gate draft → validate → approve → dispatch → audit pattern with JSON schemas, n8n workflow, and email-approval example
  • browserground — local UI-grounding specialist for hybrid AI agents: Qwen3-VL-2B LoRA, screenshot + target → strict JSON bbox. Drop-in for Claude Code, Codex, browser-use

The series

Production AI Automation Notes — a running set of repos and gists on:

  • approval gates for AI agents
  • MCP server security (permissions, tenants, audit logs)
  • Claude Code policies for company repos
  • n8n workflows with human approval
  • audit-log schemas

Follow if you're building agents that need to work outside demos.

Recent gists

Gist Topic
Claude Code persistent memory between sessions: task manager as agent memory via MCP (PAAN #3) claude mcp add / TickTick / Obsidian / PreCompact alternative / no vector DB (June 2026)
TickTick MCP server for Claude Code & Claude Desktop ticktick mcp / OAuth / exceed_query_limit / hybrid RRF retrieval (June 2026)
Obsidian vault as agent memory for Claude Code obsidian mcp / ATS_OBSIDIAN_VAULT / headless, no REST API plugin (June 2026)
Agent memory without a vector database: RRF in 15 lines of JS reciprocal rank fusion / k=60 / hit@1 bench numbers (June 2026)
AI agents that can't pick their own next action: deterministic step pipelines in Go (PAAN #10) ai agents / ai automation / deterministic / ai · approval steps / schema-validated / autonomous agent / Go (June 2026)

All gists →

Open source contributions

Project PR What
Tencent/WeKnora #835 Merged Parallel tool calling support
steveyegge/beads #2884 Merged Multi-project support, Notion sync, backup/restore
e2b-dev/infra #2273 Merged Local dev docs: prerequisites, verification steps, troubleshooting
pacifio/cersei #10 Merged Native Google Gemini provider + Cohere & SambaNova support

All merged PRs

GitHub stats


Stack: Python, Go, TypeScript, Node.js, Kubernetes, Linux, systemd, vector databases, LLM APIs.

Website: renezander.com

Production AI Automation Notes

A gist series on production-grade patterns for AI pipelines. Each entry covers one pattern with copy-pasteable code.

# Topic Pattern
#1 Agent Approval Gates Schema-validated proposals, human review, deterministic dispatch
#2 Token Budgets Per-step, per-pipeline, per-day enforcement
#3 Agentic Knowledge Base Karpathy-style LLM wiki with pluggable adapters
#4 CapCut / JianYing from an LLM agent Deterministic JSON command boundary
#5 SQLite Dedup + Crash Safety WAL mode, seen_items, audit log
#6 Prompt-Injection Defense Input sanitization, schema validation
#7 PDF Cite Verification Auditable LLM extraction with per-fragment bounding boxes
#10 Deterministic Step Pipelines Fixed typed steps; the LLM never picks the next action

Reference implementation for entries #1, #2, #5, #6, #7, #9, #10: draftcat (Go, MIT).

All gists →

Pinned Loading

  1. capcut-cli capcut-cli Public

    Independent, unofficial CLI to edit CapCut and JianYing projects — subtitles, timing, speed, volume, templates, cut long-form to shorts. No API needed, reads draft_content.json directly. Not affili...

    JavaScript 68 13

  2. draftcat draftcat Public

    Governed AI pipelines for service businesses. Deterministic-first, single Go binary, operator-approved.

    Go 5

  3. agentic-task-system agentic-task-system Public

    MCP server + CLI that turns the task manager you already use — TickTick or Obsidian — into persistent agent memory for Claude Code and any MCP client. Hybrid retrieval (RRF), no vector database to ...

    JavaScript 2

  4. agent-approval-gate agent-approval-gate Public

    Production approval-gate pattern for AI agents: draft, validate, approve, dispatch, audit. JSON schemas + n8n + email examples.

    3

  5. local-ai-coding-stack local-ai-coding-stack Public

    Scripts and configs for running Claude Code against local LLMs (Ollama, LM Studio, llama.cpp, vLLM). Companion to the local-LLM gist.

    Shell 2

  6. browserground browserground Public

    Local UI-grounding specialist for hybrid AI agents. Qwen3-VL-2B LoRA. Screenshot + text target → strict JSON bbox. Drop-in for Claude Code, Codex, browser-use. Cuts GPT-4V cost & latency.

    Python 3

AltStyle によって変換されたページ (->オリジナル) /