fireclaw/ROADMAP.md

Fireclaw Roadmap

Phase 1: Core CLI (done)

• Firecracker microVM lifecycle (boot, exec, destroy)
• SSH-based command execution
• Network isolation (tap + bridge + NAT)
• IP pool management for concurrent VMs
• Signal handling and cleanup
• CLI interface (fireclaw run, fireclaw setup)

Phase 2: Fast & Useful (done)

• Alpine Linux rootfs (1 GiB sparse, 146 MiB on disk)
• Precompiled binary, global fireclaw command
• Snapshot & restore (~1.1s vs ~2.9s cold boot)

Phase 3: Multi-Agent System (done)

• ngircd configured (nyx.fireclaw.local, FireclawNet)
• Channel layout: #control (overseer), #agents (common room), DMs, /invite
• Ollama with 5+ models, hot-swappable per agent
• Agent rootfs — Alpine + Python IRC bot + podman + tools
• Agent manager — start/stop/list/reload long-running VMs
• Overseer — !invoke, !destroy, !list, !model, !models, !templates, !status, !help
• 5 agent templates — worker, coder, researcher, quick, creative
• Agent tools — run_command, web_search (searx), save_memory
• Persistent workspace — 64 MiB ext4 as second virtio drive
• Agent memory system — MEMORY.md pattern, survives restarts
• Agent hot-reload — model/persona swap via SSH + SIGHUP
• Non-root agents — unprivileged agent user
• Agent-to-agent via IRC, DMs, /invite
• Overseer resilience — crash recovery, health checks, KillMode=process
• Graceful shutdown — IRC QUIT before VM kill
• Systemd service, regression tests

Phase 4: Hardening & Deployment (done)

• Network policies per agent — full/local/none via iptables
• Thread safety — lock around IRC socket writes
• Agent health checks — 30s interval, announces deaths in #control
• Trigger matching fix — start-of-message only
• agents.json race condition fix
• Install script — one-command deployment, battle-tested on Debian + Ubuntu
• Uninstall script
• Deployed on GPU server (Xeon + Quadro P5000)
• Refactor — shared firecracker-vm.ts helpers, -43 lines

Remaining

• Warm pool — pre-booted VMs from snapshots for instant spawns
• Concurrent snapshot runs via network namespaces
• Thin provisioning — device-mapper snapshots instead of full rootfs copies

Phase 5: Advanced Features

• Scheduled/cron tasks — agents that run on a timer
• !logs command — tail agent interaction history
• Persistent agent memory v2 — richer structure, auto-save
• Advanced tool use — MCP servers in Firecracker VMs
• Cost tracking — duration, model, tokens per interaction
• Execution recording — audit trail

Phase 6: Ideas & Experiments

See IDEAS.md for the full list. Highlights:

• MCP servers as a single Firecracker VM with podman containers
• Cron agents, webhook triggers, alert forwarding
• Agent-written agents, agent debates, dream mode
• Web dashboard, install script dry-run
• Persistent agent memory with CLAUDE.md pattern (v2)