AI Nexus

Hey IH community! 👋

I'm Michael, building AI Nexus – a professional workspace for working with AI models (think ChatGPT but with access to 100+ models, better organization, and actual workflow tools).

We've been in beta for a few months now, and something interesting happened: we started getting traction with larger teams and companies. Not the typical "2 founders in a garage" startup customers, but actual enterprise-y organizations – consulting firms, research teams, development agencies.

And they all wanted the same thing: team collaboration.

The problem:

These companies had 10-50 people all using AI Nexus. We installed a "private-cloud" version just for these companies. But those teams had zero visibility or control. They wanted to:

• Share projects and prompts across teams

• Manage who has access to what

• Consolidate billing and usage

• Actually work together instead of in silos

Fair enough. But here's the thing – I'd been avoiding building team features because:

1. It felt like scope creep (we're still in beta!)

2. I wanted to nail the individual experience first

3. Team features = complexity = slower shipping

What changed my mind:

Three specific customers came to us within the same week saying "we love this, but we need teams or we'll have to build something in-house." One was a 30-person consulting firm, another was a research lab, the third was an agency.

When you have paying customers basically begging for a feature and threatening to churn without it... you listen.

What we shipped:

The full spec is pretty detailed (happy to share if anyone's curious), but the core features:

• Team workspaces – Switch between personal and team contexts

• Project sharing – Share AI projects with granular permissions (view/comment/edit/admin)

• Team prompt libraries – Build and share effective prompts across the org

• Member management – Invite, roles (owner/admin/member/viewer), remove

The interesting part: we kept our BYOK (bring-your-own-key) model working for teams too. So enterprises can use their own Azure OpenAI, AWS Bedrock, or Google Vertex credentials. This is huge for regulated industries.

Early results:

Shipped 2 weeks ago. The three customers who requested it have already upgraded and brought their teams on. One went from 8 individual accounts to a 32-seat team plan. Another is rolling it out to 50+ people.

The interesting insight: these features aren't just for "enterprise" – we're seeing 3-5 person dev teams and small consulting shops signing up for team plans too.

What I learned:

1. Listen to paying customers – If multiple customers ask for the same thing, that's signal

2. Enterprise doesn't mean corporate – Small teams want collaboration too

3. BYOK is a moat – Letting teams use their own cloud credentials removes a huge barrier

4. Complexity is worth it – Yeah, teams added complexity, but the revenue impact justified it

What's next:

Now that teams can collaborate, the next requests are already coming in:

• Shared conversation threads (multiple people in one chat)

• Team analytics and usage tracking

• Better permission controls for sensitive projects

Honestly, I'm glad we waited until we had product-market fit with individuals before tackling teams. But once we had it, shipping teams unlocked a whole new segment.

Anyone else dealing with the "should I build team features?" question? Happy to share more details on the implementation or trade war stories.

Hey Indie Hackers!

I’m thrilled to announce a brand-new feature in AI Nexus that’s going to change how you interact with AI: Conversation Branching!

The Problem: Linear Conversations Kill Creativity

Ever sent a message to an AI, only to realize you want to tweak your question or try a different approach—but don’t want to lose the entire conversation? Most AI tools force you into a rigid, linear flow, making it impossible to experiment without starting from scratch or duplicating conversations.

The Solution: Branch by Editing Messages

With Conversation Branching, you can now:

✅ Edit any of your previous messages to create a new branch

✅ Explore alternative approaches without losing your original work

✅ Switch between branches to compare different paths

✅ Keep all context intact—including model settings and parameters

Here’s how it works:

1. Hover over any message you’ve sent

2. Click the "Edit" button

3. Modify your message to explore a new direction

4. Continue the conversation in the new branch with full context preserved

Key Detail: Each branch retains the same LLM model and parameters as the original conversation, ensuring consistency across all your explorations.

Screenshot: Branching in Action

Why This Is a Game-Changer

• For Developers: Try different code implementations or debug alternative approaches without losing your progress.

• For Writers: Experiment with different plot twists, character dialogues, or writing styles—all from the same starting point.

• For Researchers: Test hypotheses or refine questions without re-entering context.

• For Analysts: Compare how slight changes in prompts affect the AI’s output.

Built for Professionals

AI Nexus isn’t just another chat interface—it’s a powerful workspace for serious AI users. With 100+ models, project-based organization, shared context files, and now conversation branching, it’s designed for people who need more than basic chat tools.

Try It Today!

AI Nexus is currently in free beta—no credit card required. Sign up now and start branching your conversations to unlock new levels of productivity!

What do you think? How would you use conversation branching in your workflow? Let me know in the comments!

Hey IndieHackers 👋

I'm building AI Nexus - a multi-model AI interface that lets you access GPT-4, Claude, Gemini, and 100+ other models through one workspace.

One of the most frustrating problems with AI chat tools is hitting token limits in the middle of important conversations. You're deep into a complex discussion, then suddenly: "Your context is too long. Please start a new conversation."

So we built Intelligent Context Management to solve this.

The Problem

Every AI model has a context window limit (how much text it can "remember" at once). For example:

• GPT-4 Turbo: 128k tokens (~96k words)

• Claude 3.5 Sonnet: 200k tokens (~150k words)

• GPT-3.5: 16k tokens (~12k words)

When you're working on complex projects with:

• Long conversation histories

• Uploaded files (code, docs, data)

• System prompts

• Project context

...you can hit these limits fast. Most tools just error out or silently truncate your context, losing important information.

Our Solution: Smart Context Management

We built a visual context manager that shows you exactly what's using your tokens and gives you control:

What it does:

1. Real-time token tracking Visual breakdown of where your tokens are going:

• 📁 Files (project context)

• 💬 History (conversation)

• ⚙️ System prompts

• ✨ New message space

2. Intelligent auto-management Toggle on "Intelligent Context Management" and AI Nexus automatically:

• Keeps your context within limits

• Prioritizes recent messages

• Preserves important context (files, system prompts)

• Warns before truncating anything

3. Response space reservation Set how many tokens to reserve for the model's response. The UI shows you exactly how much context space remains.

4. Manual control You can see:

• Model context window: 1,000,000 tokens (in this case, Sonnet 4.5)

• Reserved for response: 415,744 tokens (41.6%)

• Available for context: 584,256 tokens

• Context used: 49,277 tokens

• Context remaining: 534,979 tokens ✅

Why This Matters

Most AI chat tools treat context as a black box. You don't know:

• How much context you're using

• What's taking up space

• When you're about to hit limits

• What gets truncated when you do

This creates anxiety and breaks complex workflows.

With transparent context management:

• ✅ No surprise errors

• ✅ Work with large files confidently

• ✅ Have longer, more valuable conversations

• ✅ Understand your costs (more tokens = higher costs)

Technical Implementation

For the curious:

Backend:

• Calculate token counts using model-specific tokenizers

• Track context across: files, messages, system prompts, tools

• Implement sliding window with semantic preservation

• Warn before auto-truncation

Frontend:

• Real-time token visualization

• Color-coded breakdown (files=blue, history=green, system=gray, new=purple)

• Responsive slider for response token reservation

• Validation against model limits

Edge cases handled:

• Different models, different context windows

• Switching models mid-conversation

• Adding/removing files

• Multi-turn conversations with tool calls

What's Next

We're quickly preparing for our free beta (3 months free, then €5/month). You bring your own OpenRouter API key and get access to 100+ models.

Other features:

• Projects - Group conversations, share context files

• Conversation branching - Explore parallel ideas

• Prompt library - Save and reuse what works

• MCP server integration - Extend with custom tools

Questions for the community:

1. How do you currently handle long conversations in ChatGPT/Claude? Start fresh? Manually summarize?

2. Would you pay for better context management? Or is this table-stakes?

3. What other context-related problems do you face? We're thinking about:

   • Auto-summarization of old messages

   • Smart context compression

   • Context presets (e.g., "keep last 10 messages + all files")

Hey IndieHackers!

Quick update on what I've been building for AI Nexus - shared memory across different AI models.

The Problem

Ever notice how you have to re-explain context every time you switch between Claude, GPT-4, and Gemini? It's like having amnesia between conversations.

Last week I was debugging an API issue:

• Started with GPT-4 to plan the approach

• Switched to Claude for code review (it's better at catching edge cases)

• Went to Gemini for some specific Google Cloud stuff

• Had to re-explain the entire context. Every. Single. Time. 🤦‍♂️

What I'm Building

Memory that persists across ALL models in AI Nexus. Here's how it works:

Basic idea: You teach something to one model, all models remember it.

Example workflow:

You → GPT-4: "I'm building a SaaS called ProjectX that does Y"
You → Claude: "What security concerns should I consider?"
Claude: "For ProjectX, given that it does Y, you should..."

Claude already knows about ProjectX. No re-explaining. 🎉

Memory Segments (The Cool Part)

I'm also experimenting with memory segments - basically folders for your AI's brain:

• Project A Segment: API endpoints, architecture decisions, deployment notes

• People Segment: Team members, their roles, communication styles

• Code Standards: Your specific linting rules, naming conventions

• Personal: Your preferences, writing style, timezone

Switch segments based on what you're working on. It's like having different workspaces for your AI assistant.

How It Actually Works

Without getting too deep in the weeds:

1. Natural language updates: "Remember that our API uses REST, not GraphQL"

2. Memories stored in markdown format (easy to read, edit, export)

3. Injected into system prompts based on active segment

4. Smart retrieval - only pulls relevant memories to save tokens

Current Status

• ✅ Basic memory persistence working

• ✅ Cross-model sharing functional

• 🔄 Building segment management UI

• 🔄 Testing memory search/retrieval

• 📋 Planning memory version control (track changes over time)

Questions for You All

1. What would you store in AI memory? I'm curious about use cases I haven't thought of

2. How would you want to organize segments? By project? By type? Both?

3. Privacy concerns? Currently memories are user-specific and encrypted, but what else?

Want to Try It?

I'm rolling this out to beta users next week. If you're already using AI Nexus (or want to start), drop a comment and I'll prioritize your access.

The goal is simple: Make AI assistants actually feel like assistants, not goldfish. 🐠

What do you think? Would this save you time?

Hey IndieHackers! 👋

I'm building something I desperately needed myself - a unified platform for managing OpenAI, Claude, and Gemini without the constant tab-switching and prompt-losing chaos.

Why I'm Building This

Like many of you, I've been integrating AI into everything I build. But the workflow is broken:

• 3+ browser tabs for different AI providers

• Copy-pasting prompts between platforms

• Losing track of what worked where

• No visibility on actual costs until the invoice hits

I needed one clean interface to manage it all. So I'm building AI Nexus.

What AI Nexus Will Do

Core features I'm shipping for launch:

• Unified access: OpenAI, Anthropic, and Gemini in one interface

• Smart prompt library: Save, organize, and reuse your best prompts

• Real-time streaming: See responses as they generate

• Transparent pricing: Pay only what you use + small margin

What makes it different:

• Built specifically for founders and developers

• No bloat - just the features power users actually need

• Usage tracking that actually helps you optimize costs

Current Status 🛠️

I'm in active development and targeting a public launch in [timeframe]. Here's where things stand:

• ✅ Core platform architecture complete

• ✅ API integrations working smoothly

• ✅ Basic prompt management system built

• 🔄 Polishing the UI for public release

• 🔄 Setting up billing and user management

• 📋 Building the waiting list

The Plan

Next 30 days:

• Finish the public-facing website

• Open early access for beta testers

• Gather feedback and iterate fast

Pricing model (keeping it simple):

• Transparent margin on API costs

• No surprise fees or hidden charges

• Optional subscriptions for heavy users

I Need Your Input! 🎯

Before I launch, I want to make sure I'm building something you'll actually use:

1. What's your biggest frustration with managing multiple AI providers?

2. What features would make you switch from your current setup?

3. How much time/money are you currently spending on AI tools?

Want Early Access?

I'm building a waiting list for IndieHackers who want to:

• Get early access when I launch

• Shape the product with direct feedback

• Lock in founder-friendly pricing

Drop a comment if you're interested and I'll make sure you're first in line when signups open!