customizable-gpt-chatbot
Reduces agent deployment friction by letting teams define capabilities in natural language rather than code, accelerating time-to-value for internal automati…
Veldra is a self-hostable, local-first agent platform: you describe what you need in plain language and it assembles a working agent with tools, MCP connectors, RAG knowledge bases, and agent teams. It is a standalone web application (Vue 3 SPA + FastAPI) with workspace sign-in and roles — not a Claude Code skill or plugin.
- Build a custom support agent by describing your workflow in plain English, no coding required.
- Create specialized chatbots for internal teams that improve accuracy through ongoing feedback and use.
- Deploy local AI agents with document search and custom tools without relying on external services.
Reduces agent deployment friction by letting teams define capabilities in natural language rather than code, accelerating time-to-value for internal automation while maintaining data sovereignty through self-hosting.
Engineering teams building internal automation tools and wanting faster iteration on agent behavior without re-engineering.
https://github.com/shamspias/customizable-gpt-chatbot
By shamspias
How to Get It
See repository README (self-hosted platform: clone the repo and deploy the FastAPI backend + Vue 3 SPA; a first-run install wizard configures the workspace, providers, and admin account).
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
After installing, paste this into Claude:
Help me build a custom support agent by describing my workflow in plain English, no coding required
Trust Signals Auto-scanned
Community Pulse Quiet
No community discussions found yet. This doesn't mean the tool isn't good — it may be new or serve a niche use case.
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
Scored from trust signals (evidence-eval-v1): 392 GitHub stars; contributors unknown; last commit 1d ago; license no license.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
- Single maintainer. Consider the risk if this person stops maintaining the project.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
Scored from trust signals (evidence-eval-v1): 392 GitHub stars; contributors unknown; last commit 1d ago; license no license.