Swamp compiles repeated agent skills into deterministic workflows, 8x fewer tokens
aigclink · x · 2026-11-17
aigclink highlights the open-source project Swamp: agents first break a task into reusable Behaviors wired into an executable Workflow, then future runs execute directly — claimed 8x token savings and 2x speedup.
- Pain point: every skill run re-reads instructions and re-plans, burning tokens with randomness and latency
- Workflows fixate tasks (e.g. server check → metrics → anomaly decision → LLM analysis if needed → report)
- Each Behavior has strongly-typed inputs/outputs, so data passed between steps is verifiable
- Deterministic steps (data fetching, threshold checks, branching) run as code; only genuinely judgment-heavy steps call the LLM
Works as skills for 9 mainstream coding agents including Claude Code, Cursor and Codex.
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