— ORDO MITHRAEUM · MMXXVI —
A modal editor, a terminal agent, and the local models that run them — three C instruments on a from-scratch inference engine. No cloud, no telemetry, no daemon. Bring your own keys, or run our weights on-device.
Plain mirror of https://mithraeums.github.io — no JavaScript, no web fonts, no third-party request. The interactive version lives at the link above; this one is for text browsers, emacs eww, and offline reading.
— I — editor · v0.1.6 · stable
A single-file modal text editor in C99. Vim-bound, language-aware, multi-pane. Embeds the hako agent in a split pane, so you can talk to a model without leaving your file.
— Modal editing · 40+ syntax modes · 18 themes · a live runner pane · OS-aware clipboard · zero runtime deps beyond libc + curl.
— II — agent · v0.2.1 · stable
A standalone terminal AI agent in one C file. Defaults to any installed hako model (hako-sho 3B / hako-koi 7B) — no key, no cloud. Adds 13 cloud providers (Anthropic OAuth, Copilot, GH Models, OpenRouter, OpenAI-compat) when you want them.
— Persistent sessions · skills as markdown · trust-gated tools · prose tool mode for small models · sha-verified self-update.
— III — models · koi live
Local-first model family. hako-sho (mini · 3B) and hako-koi (mid · 7B · Qwen2.5-Coder + hako wrap) live today on HuggingFace, tool-aware out of the box. A larger koi fine-tune (14B/32B) is queued; samurai (50B+) reserved.
— Native C engine — own loader, Q4_K/Q6_K + int8 kernels, BPE. No llama.cpp, no ggml, no ollama. The agent runs it as a one-shot hakm subprocess — no server, no daemon.
# the agent curl -fsSL https://mithraeums.github.io/hako.sh | sh # the editor curl -fsSL https://mithraeums.github.io/hake.sh | sh # the engine — build from source (libc + libm + pthread only) git clone https://github.com/mithraeums/hako && cd hako && make
Each installer fetches the latest signed release for your OS/arch, verifies the sha256 sidecar, drops the binary in ~/.local/bin. No package manager, no daemon, no telemetry.
Each is a folder in mithraeums/skills: a SKILL.md plus helpers. Markdown only — works in hako and in Claude.
reliable writes · a 3B that actually works
Whole-file writes no longer truncate — the 2048-token output cap that turned even a capable model into a “cut off → reverted → corrupt” loop is gone (tool turns floor at 8k / 4k; a stop sequence means it is never overspent). A :model arrow-key picker joins :theme / :provider, and ~/.hakorc now beats a stale global default. For small local models: auto-orient — the harness runs list_dir(".") itself when the model stalls instead of asking you to — plus a trimmed local tool set, a function-call-paren dialect, and a shape-only prompt example, so a 3B lists, reads, writes and fixes without hand-holding.
a runner pane · one thousand fewer lines
The compile loop moves in: :build / :test / :run stream into a bottom pane while you keep editing, ]e jumps straight to file:line errors, and one key hands the error to the Rei agent. :!cmd for quick one-shots. Underneath, a full lean pass — dead scaffolding out, duplicated logic folded into shared helpers, themes now a data table — ~1,000 lines lighter with the same behavior, plus real fixes: visible selection boxes on every theme, a status bar you can read, an explorer that splits instead of clobbering unsaved work.
persistent serve · KV reuse · speed
hakm --serve keeps the model resident and reuses the KV prefix across turns. Batched prefill, FMA q4k, a Q6_K int8 path, threaded attention, f16 KV — decode climbs to ~8 tok/s flat-with-depth on a CPU-only i3, warm agent turns ~3-5s (were 5+ min). Added --version. Still libc + libm + pthread, no llama.cpp, no ollama.