-
Georgia Institute of Technology
- Atlanta, GA, USA
-
09:07
(UTC -04:00) - harsha-pk.com
- @harsha_64
Stars
Python library for time series forecasting using scikit-learn compatible models, statistical methods, and foundation models
Beautiful, AI-native markdown IDE and LLM wiki
Local-first desktop markdown editor
SpaceXAI's coding agent harness and TUI. Fullscreen, mouse interactive, extensible.
turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.
YC (S26) | Record your screen 24/7 and plug into your agents. Local, private, secure. Connect to OpenClaw, Hermes agent and 100+ apps
A coding agent for open models like Kimi K3
The fastest knowledge base for growing teams. Beautiful, realtime collaborative, feature packed, and markdown compatible.
Desktop app to manage markdown knowledge bases
mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local
agent multiplexer that lives in your terminal.
A Python port of Pi’s minimalist coding agent.
Fastest and only macOS Dictation app with on-device STT and custom trained AI enhancement model. A local Wispr Flow alternative. ⭐ helps a ton :) Windows & iOS waitlist open. Linux soon.
Native Agent CLIs manager for macOS. Ghostty Terminals + Codex App Features/UX = Ghostex! Embedded browser & IDE. Strong agents support.
Official Compound Engineering plugin for Claude Code, Codex, Cursor, and more
The native macOS terminal that keeps your sessions running and tells you when a coding agent needs you. GPU-rendered, scriptable, agent-aware.
davmlaw / they_live_adblocker
Forked from uBlockOrigin/uBOL-homeReplace Ads with They Live style slogans
Lightweight coding agent that runs in your terminal
Let your agents run while your MacBook lid is closed
Muesli - local meeting transcription + dictation for macOS (Granola + WisprFlow alternative)
A native macOS app for syncing projects to your local filesystem
Vicinae extensions published to the vicinae store
microGPT benchmarks: a single M4 Max MacBook Pro P-core in C runs Karpathy's 4192-parameter transformer at ~71x the throughput of TALOS-V2's FPGA implementation.