SafeDusk
Joined 2 years ago
Karma
104
Submissions
80
Member since
Sep 17
Building https://github.com/aperoc/toolkami and https://github.com/aperoc/op-grep.
View on Hacker NewsRecent submissions
Comment · 8 months ago
Very cool! Excited to incorporate this into https://toolkami.com which is built upon RLM. Thanks for the great work!
Comment · 8 months ago
Am excited about RLM too! That's why I built https://toolkami.com so that people can try it easily for agentic workflows.
Comment · 8 months ago
Working on https://toolkami.com that enables plug and play Recursive Language Model for increased context size and better recall.
Comment · 8 months ago
Sandboxing is going to be of growing interests as more agents go “code mode”.
Will explore this for https://toolkami.com/, which allows plug and play advanced “code mode” for AI agents.
Comment · 9 months ago
If I were to add, "winter" is the best time to find snow, and there is enough snow for everyone.
Comment · 9 months ago
Not surprised OpenAI is not there, I struggled so much with telemetry in Codex that I had to build my own one Codex Plus (https://github.com/aperoc/codex-plus) -_-
Seems like it can be a standard the project can adopt.
Comment · 9 months ago
These can also be observed through OTEL telemetries.
I use headless codex exec a lot, but struggles with its built-in telemetry support, which is insufficient for debugging and optimization.
Thus I made codex-plus (https://github.com/aperoc/codex-plus) for myself which provides a CLI entry point that mirrors the codex exec interface but is implemented on top of the TypeScript SDK (@openai/codex-sdk).
It exports the full session log to a remote OpenTelemetry collector after each run which can then be debugged and optimized through codex-plus-log-viewer.
Comment · 9 months ago
Using https://github.com/aperoc/toolkami which just spins up a worktree with pre-configured Docker containers.
Comment · 9 months ago
Sad that a lot of these are for Claude Code and not Codex which I uses more, so I started https://github.com/aperoc/codex-plus which has telemetry built-in, now moving to build a Ralph loop on top of it.
Comment · 1 year ago
hehe thanks! as a self taught AI engineer, might take awhile =D
Comment · 1 year ago
UV script enabled me to distribute a MCP client or server in a single file[0].
Comment · 1 year ago
I think both Cursor and Cognition and going in the same direction of SWE-grep[0].
SWE-grep was able to hit ~700tokens/s and Cursor ~300token/s, hard to compare the precision/recall and cost effectiveness though, considering SWE-grep also adopted a "hack" of running it on Cerebras.
I'm trying to kickstart a RL-based code search project called "op-grep" here[1], still pretty early, but looking for collaborators!
[0]: https://cognition.ai/blog/swe-grep [1]: https://github.com/aperoc/op-grep