Meaning-First Compression
Keeps required evidence in the original wording—query-aware keep/drop, not a rewrite.
Cut your API Costs by 65%.
SuperCompress v2 is a query-aware compression layer that removes irrelevant context before inference. 64.1% less context · 24/24 evidence passes on coding-agent dumps — so you cut API spend without losing the lines that answer the ask.
Launch promo · 5M free tokens/mo · then $0.10/1M · no credit card
Coding-agent dumps · logs · diffs · original lines kept
Consumer AI apps send chat history, retrieved docs, tool traces, and user context on every request. That context drives LLM API cost, latency, and context-window pressure before the answer is generated. SuperCompress runs before inference, selecting the context most relevant to the current user request. Use it for chatbots, AI search, support agents, copilots, RAG, and any feature where context grows with users.
EXAMPLE: LONG CONVERSATION20,814 TOKENS
const result = await compress({
context: conversation,
query: "What failed in the last deploy?"
})
// → Neural Keep · original evidence lines retained
NEURAL V2 · HOSTED
0%+
Mean context cut
64.1% mean context cut on the coding-agent benchmark. 16,647 tokens to 5,148. Required evidence held in 24/24 cases.
GATE
24/24
Evidence held
Required evidence kept on every coding-agent case. One case cut 96.6% at ≥99% retention.
BEST AT
agents
Coding dumps
Tool output, logs, diffs, stack traces. Keeps the evidence. Does not rewrite it into a summary.
BUILT FOR DEVELOPERS
Control AI Feature Cost
Before the Model Call
Drop-In Simple
Use our API or SDK in minutes. Works with OpenAI, Anthropic, Mistral, and more.
Built for agents
Works across 40+ coding-agent harnesses. Drop in before the model call.
HOW IT WORKS
Compress before
the model call.
- 01 Ingest Chat, RAG hits, tool traces
- 02 Score Relevance vs current ask
- 03 Keep Meaning-first retention
- 04 Ship Fewer tokens to inference
Context arrives oversized — history, docs, and traces piled into one prompt.
NEURAL V2 · CODING-AGENT BENCHMARK
Cut hard.
Keep required evidence.
We measure evidence containment — not downstream LLM completion. Full methodology on /benchmarks.
Full methodology →
METHODMEAN TOKEN CUT
(HIGHER IS BETTER)EVIDENCE PASS
(B5 · 24 CASES)HOW IT WORKS
(HIGHER IS BETTER)EVIDENCE PASS
(B5 · 24 CASES)HOW IT WORKS
SuperCompress v2
64.1%
24/24
Query-aware keep · before inference
LLMLingua-2
52.7%
12/24
Token pruning · can drop evidence
Truncation
64.3%
11/24
Head/tail only · blind to the ask
Headroom 0.36.4
14.8%
18/24
Type / tool-output heuristics
Neural v2 B5 (coding-agent): 64.1% mean cut, 24/24 evidence passes, 16,647 → 5,148 tokens. Evidence containment — not downstream completion. Details on /benchmarks.
curl -X POST https://api.supercompress.dev/compress \
-H "Authorization: Bearer $SC_LIVE_..." \
-H "Content-Type: application/json" \
-d '{
"context": "$(cat conversation.txt)",
"query": "What failed in the last deploy?"
}'// Response · Neural Keep (hosted)
{
"compressed": "...",
"original_tokens": 16647,
"compressed_tokens": 5148,
"tokens_saved_pct": 64.1,
"engine": "neural-keep-v2"
}
Cursor
Claude Code
Codex
Gemini CLI
Windsurf
VS Code
Copilot
OpenCodeEvery coding agent. One compression layer.
CODING AGENT PLUGIN · MCP-FIRST
One Install. Every Agent.
Fewer Tokens.
Auto-detect Cursor, Claude Code, Codex, OpenCode, Windsurf, and more. The MCP plugin compresses huge dumps before they burn tokens — keep your normal login.
Or the long name: npm install -g supercompress-proxy then supercompress setup.
$
npx -y supercompress-ai setup- ✓ Works across 40+ coding-agent harnesses
- ✓ MCP plugin installed
- ✓ Works with login — no API-key mode
USE CASES
Use Cases That
Compound
From agentic coding to document-heavy work, meaning-first compression helps teams do more with less—without losing what matters.
Coding Agents
Compress task history, repo context, tool traces, and diffs so agents reason farther inside the same context window—and spend less per turn.
- Shrink multi-file diffs before the model call
- Keep plans + decisions, drop stale tool noise
- Works as an MCP plugin across Cursor, Claude Code, Codex
Long Conversations
Keep long chats useful and coherent. SuperCompress retains the decisions, constraints, and facts that drive better answers—not every filler turn.
- Lower cost on multi-hour support or sales threads
- Preserve user preferences and prior commitments
- Reduce latency as history grows
RAG & Search
Retrieved chunks often drown the query. Compress retrieved context so the model sees the evidence that matters for the current ask.
- Cut redundant passages across top-k results
- Keep citations and key claims intact
- Fit more evidence into the same budget
Support Copilots
Ticket history, macros, and knowledge-base hits add up fast. Compress before generation to keep replies accurate without burning tokens.
- Prioritize current issue + account state
- Drop repeated boilerplate from prior tickets
- Ship faster replies at lower per-ticket cost
Document Workflows
Specs, tickets, research notes, and PRDs are dense. Compress for reviews and synthesis while retaining requirements and decisions.
- Faster design and compliance reviews
- Keep must-have constraints and open questions
- Pair with human-in-the-loop editing
Production Inference
Query-aware keep before every model call — shrink context, keep the evidence lines.
- Compress context before the provider call
- 64.1% mean B5 cut · 24/24 evidence containment
- Drop-in before OpenAI, Anthropic, and more
Live polling…
—
tokens processed
across SuperCompress · updates as people compress
SuperCompress
Ship AI features with lower per-request cost.
Launch promo · 5M free tokens/mo · then $0.10/1M · no credit card.