Keep large tool output out of LLM context: 3x accuracy 95% fewer tokens
LLM agents often place raw JSON tool outputs directly in the prompt. After a few tool calls, earlier results get compacted or truncated and answers become incorrect or inconsistent. I built Sift, a drop-in MCP gateway that stores tool outputs as local artifacts (filesystem blobs indexed in SQLite) and returns an `artifact_id` plus compact schema hints when responses are large or paginated. Instead of reasoning over full JSON in the prompt, the model runs a small Python query: def run(data, schema, params): return max(data, key=lambda x: x["magnitude"])["place"] Query code runs in a…
In plain words
Sift is an MCP gateway that improves LLM agent accuracy by storing tool outputs as local artifacts instead of placing raw JSON directly in prompts. When responses are large or paginated, it returns a compact artifact ID and schema hints, allowing the model to run small Python queries on the data instead of reasoning over full JSON in the context window. This approach prevents information loss from prompt truncation. It's designed for developers building LLM agents who need consistent, accurate reasoning across multiple tool calls.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
LLM agents often place raw JSON tool outputs directly in the prompt. After a few tool calls, earlier results get compacted or truncated and answers become incorrect or inconsistent. I built Sift, a drop-in MCP gateway that stores tool outputs as local artifacts (filesystem blobs indexed in SQLite) and returns an `artifact_id` plus compact schema hints when responses are large or paginated. Instead of reasoning over full JSON in the prompt, the model runs a small Python query: def run(data, schema, params): return max(data, key=lambda x: x["magnitude"])["place"] Query code runs in a constrained subprocess (AST/import guards + timeout/memory caps). Only the computed result is returned to the model. Benchmark (Claude Sonnet 4.6, 103 questions across 12 datasets): - Baseline (raw JSON in prompt): 34/103 (33%), 10.7M input tokens - Sift (artifact + code query): 102/103 (99%), 489K input tokens Open benchmark + MIT code: https://github.com/lourencomaciel/sift-gateway Install: pipx install sift-gateway sift-gateway init --from claude Works with Claude Code, Cursor, Windsurf, Zed, and VS Code. Existing MCP servers and tools require no changes.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
