Foci
Description
openclaw-like ai agent platform. Written in go for speed and memory-efficiency. Supports claude code as backend, or APIs. Protects your secrets from being read by your agents or otherwise leaked!
Installation
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open the source below and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
README
Foci
**One binary. ~35 MB idle. No framework.**
AI agents on Telegram and Discord, written in Go.
[Quick Start](#quick-start) · [Design](#design) · [Docs](#documentation)
Inspired by [OpenClaw](https://github.com/openclaw/openclaw), built from scratch in Go — single binary, cache-first, with OS-level secret isolation. Session branching, tool piping, and coding agent orchestration go well beyond the original. Built for Anthropic, but any OpenAI-compatible endpoint works.
Quick Start
git clone https://github.com/richardtkemp/foci.git && cd foci && sudo make setupSee [docs/INSTALL.md](docs/INSTALL.md) for prerequisites, options, and next steps.
Background
OpenClaw is the established, full-featured choice in this space — broad provider support, native apps on every platform, a marketplace of 13,000+ skills, and a large community. Foci makes different bets. Where OpenClaw optimizes for breadth, foci optimizes for depth: cache-aware prompt architecture, OS-level secret isolation, and a codebase small enough that one person can audit the whole thing. See [docs/COMPARISON.md](docs/COMPARISON.md) for a detailed feature comparison.
| OpenClaw | Foci | |
|---|---|---|
| Runtime | Node.js + TypeScript | Go, single binary |
| Memory | ~500MB+ idle | ~35 MB |
| Dependencies | ~560 packages (594MB) | 22 direct modules |
| Startup | Seconds (transpile + boot) | Instant |
| Config | YAML + env + scattered files | One TOML file |
| Cache strategy | Not cache-aware | Day-zero architectural |
Fewer moving parts means fewer surprises. Secret management follows the same principle: OS-level isolation, domain-locked credentials, redaction at every layer — protection that doesn't depend on trusting the model.
