Diti Chat

Low-friction channel (iMessage) to a personal agent that can remember context and act through vetted third-party APIs by @Juls95

[Julian R. @Juls95]

@fiwing_chat is now ready to use! 🚀
This project was never about shipping “just another AI chatbot.”
It was always about building a trustworthy operational loop with strong memory, rock-solid identity discipline, and real tool execution. Thanks for making this challenge! @lablabai @AIatAMD

Here’s what we solved:

- Adjusted Spectrum Cloud behavior from @photon_hq to avoid webhook blocking while keeping ingestion perfectly aligned with stream handling.
- Made @composio foundational (not optional). Fiwing only stores ca_* references and never touches raw OAuth tokens directly.
- Inference runs on @AMD @FireworksAI_HQ + @Alibaba_Qwen -family models with full env-driven switching — cheap experimentation and low rollout risk.
- Security posture is tight: no raw tokens in the app DB, strict account scoping, and explicit state transitions for connection readiness.

Result?
Fiwing now behaves like a true integrated system instead of disconnected components. Identity, memory, model runtime, and tools all converge cleanly in one reliable loop.
The hardest part is done: we have stable end-to-end behavior with durable auth state and real tool use.
Next up: scale hardening and UX refinement.
Super excited about where this is heading!

#BuildInPublic #AI #DigitalTwin #PhotonHQ #Composio

[Diti Chat @ditichat]

We started with one simple product belief: the most useful AI is the one already inside your daily behavior. For most people, that channel is messaging, not a dashboard.🧑‍💻
Fiwing needed persistent per-user memory from day one. And tool access must be real and secure. 🔐

[Julian R. @Juls95]

Last week I saw a post from @lablabai promoting a hackathon using @AIatAMD + @Alibaba_Qwen tools… and it instantly sparked an idea: build a real #personalAIagent.
I spent the next 5 days planning it and 2 develolpin. I got inspired by @0xJuliechen 's project — a chat that felt like you were actually talking to a famous person through their quotes. That magic made me create @fiwing_chat .
Here’s the architecture I’m building:
The inbound path is powered by Spectrum Cloud stream consumption via @photon_hq 🔥 This decision removes one external UI dependency from the critical request path.

User identity is normalized early: @supabase user id(UUID) is the canonical key. Phone = routing. space_id = conversation thread context.
Clear separation. No duplicate users. No cross-thread contamination. No identity headaches.

Memory path is fully per-user and pulled on every single turn thanks to @honchodotdev. Context retrieval isn’t “best effort” — it’s an explicit, non-negotiable stage before generation.
Inference runtime runs on @FireworksAI_HQ through @AMD using the @Alibaba_Qwen family (model selection via env vars). Switching providers or models is now just a config change, not code surgery.

@composio is mandatory in the execution flow. If the required tools aren’t available, the system degrades explicitly instead of hallucinating capabilities.
Security boundary: the app only stores ca_* references. OAuth tokens stay inside Composio’s boundary — minimizing blast radius.

Operationally, this is deploy-safe, observable, and built with explicit control points.
Day 1 delivered a solid systems baseline: channel + identity + memory + model + tooling, all integrated.

This is how you build a true Digital Twin that actually feels personal and secure.

Who else is building their own AI agent right now? Drop your stack below 👇
#BuildInPublic #AI #DigitalTwin #AMD #PHOTONHQ