Initial commit — fireclaw multi-agent system

Firecracker microVM-based multi-agent system with IRC orchestration and local LLMs.

Features:
- Ephemeral command runner with VM snapshots (~1.1s)
- Multi-agent orchestration via overseer IRC bot
- 5 agent templates (worker, coder, researcher, quick, creative)
- Tool access (shell + podman containers inside VMs)
- Persistent workspace + memory system (MEMORY.md pattern)
- Agent hot-reload (model/persona swap via SSH + SIGHUP)
- Non-root agents, graceful shutdown, crash recovery
- Agent-to-agent communication via IRC
- DM support, /invite support
- Systemd service, 20 regression tests

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

TODO.md

@@ -0,0 +1,38 @@
+# TODO
+
+## Done
+
+- [x] Firecracker CLI runner with snapshots (~1.1s)
+- [x] Alpine rootfs with ca-certificates, podman, python3
+- [x] Global `fireclaw` command
+- [x] Multi-agent system — overseer + agent VMs + IRC + Ollama
+- [x] 5 agent templates (worker, coder, researcher, quick, creative)
+- [x] 5 Ollama models (qwen2.5-coder, qwen2.5, llama3.1, gemma3, phi4-mini)
+- [x] Agent tool access — shell commands + podman containers
+- [x] Persistent workspace + memory system (MEMORY.md pattern)
+- [x] Agent hot-reload — model/persona swap via SSH + SIGHUP
+- [x] Non-root agents — unprivileged `agent` user
+- [x] Agent-to-agent via IRC mentions (10s cooldown)
+- [x] DM support — private messages, no mention needed
+- [x] /invite support — agents auto-join invited channels
+- [x] Channel layout — #control (commands), #agents (common), DMs
+- [x] Overseer resilience — crash recovery, agent adoption
+- [x] Graceful shutdown — IRC QUIT before VM kill
+- [x] Systemd service (KillMode=process)
+- [x] Regression test suite (20 tests)
+
+## 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
+
+- [ ] Fix trigger matching — only trigger when nick is at the start of the message, not anywhere in text. Currently "say hi to worker" triggers worker even when addressed to another agent.
+- [ ] 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