abc91bc149
Add dangerous command blocking and cron agent scheduling
...
Dangerous command approval: run_command skill now checks commands
against 9 regex patterns (rm -rf /, dd, mkfs, fork bombs, shutdown,
device writes, etc.) and blocks execution with a clear message.
Defense-in-depth layer on top of VM isolation.
Cron agents: templates support schedule (5-field cron) and
schedule_timeout (seconds, default 300) fields. Overseer checks
every 60s, spawns {name}-cron agents on match, auto-destroys after
timeout. Inline cron parser supports *, ranges, lists, and steps.
No npm dependencies added.
2026-04-08 19:26:23 +00:00
c827d341ab
Overhaul agent quality — prompts, tools, config, compression
...
- Rewrite system prompt: structured sections, explicit tool descriptions
with full SKILL.md descriptions, multi-agent awareness
- Add write_file skill for creating/modifying workspace files
- Per-template config passthrough: temperature, num_predict, context_size,
compress settings, max_tool_rounds, max_response_lines
- Bump defaults: 1024 output tokens (was 512), 500-char deque (was 200),
250-token summaries (was 150), compress threshold 16 (was 12), keep 8 (was 4)
- Cache compression by content hash — no redundant summarization
- Update all 5 templates with tuned settings per role
2026-04-08 18:28:26 +00:00
6673210ff0
Add remaining low-priority items from code review to TODO
2026-04-08 02:00:06 +00:00
3c00de75d1
Update TODO with prioritized next items
2026-04-07 20:50:19 +00:00
2e5912e73c
Add refactoring note to TODO
2026-04-07 16:32:32 +00:00
50b8c7464b
v0.1.2 — multi-agent system with hardening
...
Bump version to 0.1.2. Update description and polish TODO.
Since v0.1.0:
- Multi-agent IRC orchestration (overseer + agent VMs)
- 5 agent templates, 5 Ollama models
- Tool access (shell + podman containers)
- Persistent workspace + memory system
- Agent hot-reload, non-root agents
- Thread safety, health checks, network policies
- Trigger matching fix, race condition fix
- Graceful shutdown, crash recovery, systemd service
- DM support, /invite, agent-to-agent communication
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com >
2026-04-07 14:31:27 +00:00
ff694d12f6
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 >
2026-04-07 13:28:29 +00:00
