ContextOps for coding agents

Less tokens.
More signal.

Coding agents burn tokens on raw tool output, repeated context, and forgotten decisions. Mega Saver compresses what the model doesn't need — without hiding what it does — across Claude Code, Cursor, Codex, and any CLI agent. Local-first. No account, no cloud.

$npm i -g @megasaver/cli star on github ↗
then mega init — hooks, MCP bridge, and the dashboard in one command.
 PostToolUse · Read src/server.ts
what the agent read
import { createServer } from "node:http";
import { readFileSync, watchFile } from "node:fs";
import { parse } from "node:url";
// … 240 more lines of imports, types,
// route handlers, error mapping, tests …
export function createServer(opts) {
  const app = http.createServer(handler);
  app.listen(opts.port, "127.0.0.1");
  return app;
}
// 3,981 tokens of file the model half-needs
what Mega Saver sends
createServer(opts) → binds 127.0.0.1:opts.port,
returns the http server. Imports: http, fs
(readFileSync, watchFile), url.parse.

Full output recoverable —
proxy_expand_chunk("cs_9f2", "0").
3,981 → 214 tokens 94% lighter ranked by your project's memory, not a blind truncation nothing lost — the raw chunk is one call away
the receipt

It keeps the receipt, and the receipt is honest.

Every compression is measured. The dashboard turns saved tokens into a number you feel — and labels every dollar an estimate, because that's what it is.

$12.30 /wk (est.)
would-have-paid input
4.1M
tokens saved
68%
avg reduction
≈20
context windows reclaimed

Saved tokens are output the model never received, so — unlike a metered bill — they carry no prompt-cache discount to double-count. The dollar figure is estimated at a representative input rate and floored, never rounded up. Conservative by construction.

why it's different

Others prune output. Mega Saver prunes with your project's memory — and never strips what the model needs to decide.

evidence-preserving

Compression that can't lie

Every compressed result is expandable back to the complete, original text. Re-read an unchanged file and it returns a lossless pointer, not a re-summary. It saves tokens; it never blinds the model.

cross-agent memory

Learn once, every agent inherits

What Claude Code learns about your repo today, Codex, Cursor, and Aider inherit tomorrow — one approved, human-gated memory store shared across every agent through thin connectors.

decision-trace

See why each context happened

No agent shows why a decision was made. Mega Saver does: which memory boosted a chunk, the ranking scores, the redaction — the causal chain behind every output, in the CLI and a graph.

local-first

Your machine, your keys

No database, no account, no cloud. Secrets are redacted before anything is stored. The optional metering proxy records token counts only, over your own API key, on loopback.

Stop paying for tokens the model never reads.

$npm i -g @megasaver/cli && mega init github ↗
Reduce Claude Code token usage today — free, open source (MIT), works with the agents you already use.