DEV Community

Jackson Ly profile picture

Jackson Ly

Solo founder building recal: a local-first Mac assistant that does your busywork on-device, 0 bytes leave your machine. It proposes, you approve. Building in public. recal.so

Joined Joined on 
Refreshing a token I did not own logged our account out

Refreshing a token I did not own logged our account out

Comments
4 min read

Want to connect with Jackson Ly?

Create an account to connect with Jackson Ly. You can also sign in below to proceed if you already have an account.

Already have an account? Sign in
A 200 response is not a page, and your policy check is grepping an empty shell

A 200 response is not a page, and your policy check is grepping an empty shell

1
Comments 3
4 min read
Your agent's inbox check is measuring read state, not answered state

Your agent's inbox check is measuring read state, not answered state

1
Comments 4
4 min read
Durable approval is not the same as valid approval

Durable approval is not the same as valid approval

6
Comments
3 min read
Running local and cloud models in the same coding agent: what actually ships in 2026

Running local and cloud models in the same coding agent: what actually ships in 2026

Comments
4 min read
Your interval-triggered agent pays full price for empty runs

Your interval-triggered agent pays full price for empty runs

Comments
4 min read
Human in the loop is not a switch: classify the commands

Human in the loop is not a switch: classify the commands

Comments
4 min read
Your cache_read_input_tokens is zero. Here is what silently did it.

Your cache_read_input_tokens is zero. Here is what silently did it.

1
Comments 2
5 min read
Your baseline scored 0.000. That's a broken harness, not a result.

Your baseline scored 0.000. That's a broken harness, not a result.

Comments 3
4 min read
Our Rust file watcher ate 23.6 GB of RAM, and our ignore rules never had a chance

Our Rust file watcher ate 23.6 GB of RAM, and our ignore rules never had a chance

Comments 3
4 min read
Point any app at a local LLM on your Mac (OpenAI-compatible endpoints)

Point any app at a local LLM on your Mac (OpenAI-compatible endpoints)

Comments
4 min read
MLX vs GGUF on Apple Silicon: which local LLM format should you actually use?

MLX vs GGUF on Apple Silicon: which local LLM format should you actually use?

Comments 1
4 min read
What belongs in an agent's context window (and what to evict)

What belongs in an agent's context window (and what to evict)

3
Comments 16
4 min read
What poisoning a RAG store taught us about agent memory

What poisoning a RAG store taught us about agent memory

1
Comments 2
7 min read
Why I built my Mac assistant to run 100% on-device (and what local-first actually cost me)

Why I built my Mac assistant to run 100% on-device (and what local-first actually cost me)

1
Comments 9
4 min read
loading...