Swamp compiles repeated skills into deterministic workflows: 8x fewer tokens, 2x faster
aigclink · x · 2026-11-17
Open-source project Swamp (831 GitHub stars) tackles the waste in running AI skills: every run, the model re-reads instructions, re-plans, and re-decides each step — burning tokens, adding randomness, and slowing things down.
- Agent first decomposes a task into reusable Behaviors, then chains them into an executable Workflow; subsequent runs execute directly
- Example: server status check → fetch metrics → threshold comparison → call LLM only to analyze anomalies → generate report
- Each behavior has strongly-typed inputs/outputs, making data passed between steps explicitly verifiable
- Deterministic operations (data fetching, threshold checks, branching) run as plain code; LLM calls are reserved for steps that genuinely need reasoning
- Supports Claude Code, Cursor, Codex and more
More from coding & agent
- Claude Code demolished Microsoft's decade-long VS Code strategy in under 6 months, says Gergely Orosz — rickasaurus · 2026-11-17
- Personal agent checks email every 5 minutes on DeepSeek V4.1 Flash at near-zero cost — alexcovo_eth · 2026-11-17
- AI-generated code passes all tests but is riddled with opaque contracts, finds Stanford professor's review — RobbWiller · 2026-11-17
- Riley Brown: After 50+ DMs, Nothing Beats Claude Code Projects Right Now — angrypenguinPNG · 2026-11-17
- MCP server turns your saved reels and posts into searchable notes for Claude — PaRtHuS · 2026-11-17
- Stardock CEO shows agents building games across PCs and Macs, with hard-won engineering lessons — draginol · 2026-11-17