Your agent isn't running out of context because of one big file

A developer built Context Diet, an open-source MCP server and CLI that deterministically shrinks the content AI agents send by deduplicating, extracting and extractively summarizing text while keeping every output line verbatim and accounting for each dropped line in a manifest. On a sample session log packed to a 400-token budget with the query "test failure," the tool cut 169 lines and 7,917 bytes (about 1,942 estimated tokens) down to 23 lines and 1,587 bytes (about 392 estimated tokens), with the manifest reconciling 23 kept, 54 deduped, 4 extracted away and 88 summarized away. The MIT-licensed tool runs locally with no model calls or network access and is distributed via GitHub, with an npm package planned.

Your agent isn't running out of context because of one big file. It is running out because of accumulation: tool outputs, test logs, build logs, repeated turns, and the same content pasted again in a slightly different form. I kept watching sessions die on the tenth retry of the same failing test — not because any single output was huge, but because nobody ever threw anything away. So I built Context Diet: an MCP server plus a CLI that shrinks the content an agent actually sends, deterministically, with receipts. Every output line is copied verbatim from the input. Every dropped line is counted and categorized in a manifest. No model, no download, no data leaves the machine. Five tools, one promise — nothing invented: diet count — lines, bytes, and estimated tokens of a text. diet dedupe — removes exact duplicate lines and repeated blocks. diet extract — relevance-ranked excerpts for a query, with context around each hit. diet summarize — an extractive summary to a token budget. It keeps headings, error and failure lines, and the first and last lines of each section. It never rewrites a word. diet pack — the full pipeline: dedupe, then extract if you give it a query, then summarize to a budget, plus a manifest for every line. The manifest is the point. A summary that silently rewrites your log is a liability; a summary that says "kept 23 lines, dropped 54 as duplicates, 4 in extraction, 88 in summarization" is something you can diff and trust. On a real session log verbose test runs, a README excerpt, a build output — examples/session.log in the repo , packed to a 400-token budget with the query test failure : | | Lines | Bytes | Est. tokens | |---|---|---|---| | Before | 169 | 7,917 | 1,942 | | After | 23 | 1,587 | 392 | Token counts are estimates a documented chars/4 rule ; lines and bytes are exact. The manifest adds up: 169 = 23 kept + 54 deduped + 4 extracted away + 88 summarized away. Verbatim: true. From source the npm package arrives with the first npm publish : git clone https://github.com/techdevfun/context-diet cd context-diet npm install && npm run build node dist/cli.js pack --input examples/session.log --budget 400 --query "test failure" As an MCP server over stdio, point your client at node /path/to/context-diet/dist/server.js . The repo has a demo GIF recorded from a real terminal session, CI on Node 20 and 22, and a test suite that runs the server through a real MCP client. This is a crowded corner, and the honest version is that each rival is better at something: Plainly: LLMLingua compresses harder than our typical 2–5x on logs. mcp-token-optimizer understands code structure and restores formatting; we treat code as text. Entroly covers whole codebases with a dashboard; we are one focused pipeline. Vendor tool search fixes tool-schema bloat at percentages we will never match, because that is not our layer. We do not have those things in v1, and we do not claim them. What we have instead is the one thing none of them offer: a deterministic, auditable diet for session content, where every cut is accounted for and nothing is invented. LLM summarization opt-in , model-based compression, AST-aware code minification, cross-session cache, dashboard, auto-apply to agent configs, JUnit/XML parsing, SARIF output, secret redaction. Repo: https://github.com/techdevfun/context-diet https://github.com/techdevfun/context-diet — MIT licensed, no account, no network, no model calls. If your sessions also die by accumulation, try it on your own ugliest log and check the manifest.