Local-first, private AI agent workspace for Codex and Claude. Own your context and run agents on your Mac.
⑂ 6◎ 14
Archive
Derived from this repo's Cargo dependencies and activity — difficulty is an estimate from codebase size and scope.
Matched by dependency overlap in Cargo manifests — each card notes the most distinctive crates both projects share.
Local-first, private AI agent workspace for Codex and Claude. Own your context and run agents on your Mac.
memra — from-scratch LLM inference engine for NVIDIA RTX 50-series (Rust + CUDA)
From-scratch Rust+CUDA inference engine, bit-exact by construction — NVFP4, MoE, MTP speculative decoding, tuned against measured limits of one RTX 5090 Laptop (sm_120a).
Advanced configuration options for sockets.
MLX-based experimental inference engine
CodeSeeX is a local desktop bridge that lets Codex run DeepSeek V4 with 1M context, Codex tool compatibility, built-in Web Search, and a ready-to-copy config.toml setup.
Open-Source Platform for Subagents and Agent Teams. Long-running, collaborative, proactive.
Open Source Agentic Coding Harness