Optiforce strips the fluff before it reaches Claude — old tool outputs, stale history, and bloated thinking blocks that pile up with every agent step. Same results. 40% fewer tokens.
Claude Code appends every tool output and result to the context window with no pruning. By step 10, the model is reading your step 1 bash output. That's your token budget.
Each agent iteration appends tool outputs, results, and reasoning — without any pruning or relevance check.
Early steps that no longer matter remain in the prompt, consuming tokens that could go toward what's relevant now.
As context accumulates, the model's attention spreads thin over outdated content instead of focusing on the current task.
Every redundant token costs money and burns rate-limit capacity — regardless of whether it contributes to the output.
Optiforce runs as a lightweight HTTPS proxy alongside Claude Code. No changes to your code or workflows.
Each request is analyzed in real-time. Prior context is ranked by relevance to the current step. Low-signal history is compressed out.
A focused, high-signal prompt reaches Anthropic's API. Context stays bounded across the entire agent run — automatically.
Per-command savings measured across 13,000+ real compactions. Every bar is a real tool call — left is what Claude Code sent, right is what Optiforce forwarded.
Head-to-head on SWE-bench Verified against RTK v0.35.0 — the leading open-source context compressor. Optiforce cuts more tokens while matching or exceeding task quality.
| Task | RTK v0.35.0 | Baseline (no compression) | Optiforce |
|---|---|---|---|
| astropy | 1.98M tokens· reward 0.60 | 1.84M tokens· reward 0.85 | 1.06M tokens· reward 0.85-47% vs RTK |
| django | 2.71M tokens· reward 0.95 | 2.21M tokens· reward 0.91 | 1.38M tokens· reward 0.91-49% vs RTK |
| matplotlib | 1.68M tokens· reward 0.95 | 1.65M tokens· reward 1.00 | 0.93M tokens· reward 1.00-45% vs RTK |
Stay focused during long Claude Code runs. Plug in once and immediately get more from every session — no configuration needed.
Predictable token usage, consistent agent behavior, and full observability into context selection — across your entire organization.
Your source code and context content are never stored. Only anonymized per-command-type statistics are retained temporarily for your dashboard.
Aggregated usage statistics — which command types waste context, how much was saved — are kept for a limited time to power your dashboard, then discarded.
Works as a transparent proxy alongside Claude Code. No modifications to your codebase, workflows, or tooling.
An external optimization layer that adds minimal latency and delivers maximum signal improvement at every step.
Start optimizing your Claude Code context today. Free for individuals.