fireclaw/TODO.md

TODO

Done

• Firecracker CLI runner with snapshots (~1.1s)

• Alpine rootfs with ca-certificates, podman, python3

• Global fireclaw command

• Multi-agent system — overseer + agent VMs + IRC + Ollama

• 5 agent templates (worker, coder, researcher, quick, creative)

• 5 Ollama models (qwen2.5-coder, qwen2.5, llama3.1, gemma3, phi4-mini)

• Agent tool access — shell commands + podman containers

• Persistent workspace + memory system (MEMORY.md pattern)

• Agent hot-reload — model/persona swap via SSH + SIGHUP

• Non-root agents — unprivileged agent user

• Agent-to-agent via IRC mentions (10s cooldown)

• DM support — private messages, no mention needed

• /invite support — agents auto-join invited channels

• Channel layout — #control (commands), #agents (common), DMs

• Overseer resilience — crash recovery, agent adoption

• Graceful shutdown — IRC QUIT before VM kill

• Systemd service (KillMode=process)

• Regression test suite (20 tests)

• Refactor duplicated code — waitForSocket, boot sequence, tap setup, rootfs mount/inject are copy-pasted across vm.ts, snapshot.ts, agent-manager.ts. Extract shared helpers.

Next up

• Network policies per agent — restrict internet access
• Warm pool — pre-booted VMs for instant agent spawns
• Persistent agent memory improvements — richer memory structure, auto-save from conversations
• Thin provisioning — device-mapper snapshots instead of full rootfs copies

Polish

• Agent-to-agent response quality — small models (7B) parrot messages instead of answering. Needs better prompting ("don't repeat the question, answer it") or larger models (14B+). Claude API would help here.
• Cost tracking per agent interaction
• Execution recording / audit trail
• Agent health checks — overseer pings agents, restarts dead ones
• Thread safety in agent.py — lock around IRC socket writes
• Update regression tests for new channel layout