io.github.shivam-app-developers/ai-optimizer
MCP server that cuts AI coding agent token usage via framework-aware context optimization
Installation
Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).
@ai-optimizer/coreclaude mcp add ai-optimizer -e 'AI_OPTIMIZER_LICENSE=<your ai_optimizer_license>' -e 'AI_OPTIMIZER_LSP=<AI_OPTIMIZER_LSP>' -e 'AI_OPTIMIZER_TELEMETRY=<AI_OPTIMIZER_TELEMETRY>' -- npx -y @ai-optimizer/core@0.1.0{
"mcpServers": {
"ai-optimizer": {
"command": "npx",
"args": [
"-y",
"@ai-optimizer/core@0.1.0"
],
"env": {
"AI_OPTIMIZER_LICENSE": "<your ai_optimizer_license>",
"AI_OPTIMIZER_LSP": "<AI_OPTIMIZER_LSP>",
"AI_OPTIMIZER_TELEMETRY": "<AI_OPTIMIZER_TELEMETRY>"
}
}
}
}Variables d'environnement
AI_OPTIMIZER_LICENSEsecret Ed25519 JWT license key. Unlocks Pro/Team packs; free tier needs no key.AI_OPTIMIZER_LSPSet to 0 to disable the LSP bridge (optimized_diagnostics).AI_OPTIMIZER_TELEMETRYSet to 'on' to enable anonymous opt-in telemetry. Off by default.
Documentation
Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.
AI Token Optimizer
An MCP server that cuts AI coding-agent token usage by 60–80% via framework-aware context optimization.
AI coding agents read whole files when they need 15 lines. They load *.g.dart,
R.java, node_modules/, and dist/ into context — then do it again next turn.
AI Token Optimizer is a Model Context Protocol
server that intercepts those tool calls and strips framework noise before it
reaches the model.
Works with anything that speaks MCP: Claude Code, Cursor, Cline, Continue, Zed, JetBrains AI, GitHub Copilot agent mode, Antigravity, Windsurf, OpenAI Codex CLI.
Quickstart
npm install -g @ai-optimizer/coreThen point your agent at the ai-optimizer stdio server. For Claude Code, add to
~/.claude/settings.json:
{
"mcpServers": {
"ai-optimizer": {
"command": "ai-optimizer"
}
}
}Or scaffold the config and preview your savings automatically:
npx @ai-optimizer/init
# "we'd skip 47 files, ~14K tokens/session, ~$0.42/session at Sonnet pricing"Full per-agent setup (Cursor, others), LSP install, and verification steps live in
packages/core/README.md.
What it does
It registers tools the agent uses instead of its built-in file/dir/error reads:
| Tool | What it saves |
|---|---|
optimized_read_file | Framework-aware skip + optional line slice |
optimized_list_files | Walks the tree applying ignore globs (+ .gitignore) |
optimized_grep | Content search scoped by ignore filters |
optimized_diagnostics | Spawns the right LSP, returns errors + a narrow code window |
read_symbol | LSP workspace/symbol slice instead of a full-file read (Pro/LSP) |
strip_bash_noise | Strips ANSI, npm/maven/gradle progress, JVM warnings |
optimizer_status | Detected frameworks, active packs, cumulative tokens saved |
When a project type is detected (e.g. Python via pyproject.toml), the matching
pack's ignore rules activate automatically. .gitignore is respected on top.
Tiers
| Free (MIT core) | Pro ($9/mo) | Team ($29/seat) | |
|---|---|---|---|
| Framework packs | Python, JS/TS | + React, Flutter, Java, Kotlin, Go, Rust, C#, Swift, Ruby, Elixir, PHP, Solidity | all Pro packs |
| History compaction | — | ✓ | ✓ |
Scheduler (claude -p cron) | — | ✓ | + work-stealing across providers |
| Audit log + secret redaction + policy | — | — | ✓ |
See PRICING.md. Behavior-changing or data-sharing features
(scheduler, work-stealing, telemetry) are off by default and require explicit
opt-in. Display-only features (dollar-value savings) default on.
Monorepo layout
| Package | Purpose | Published |
|---|---|---|
packages/core | MCP server + free packs | npm (MIT) |
packages/init | npx @ai-optimizer/init config + savings preview | npm |
packages/sdk | definePack plugin SDK | npm |
packages/context-mode-import | Import .contextmode configs | npm |
packages/pro | Pro/Team packs + scheduler + audit | private |
apps/landing, apps/dashboard, apps/vscode-extension, apps/license-server | Site, local dashboard, IDE widget, license issuance | private |
tools/pack-bench | Pack quality benchmark harness | private |
Architecture details: ARCHITECTURE.md.
Development
npm install # at repo root (workspaces)
npm run build # build all packages
npm test # run all test suitesSecurity
Local-only by design — license validation is the only network call. Report
vulnerabilities per SECURITY.md.
License
Core engine is MIT — see LICENSE. Pro/Team packs are proprietary.
Questions fréquentes
Qu'est-ce que io.github.shivam-app-developers/ai-optimizer ?
MCP server that cuts AI coding agent token usage via framework-aware context optimization
Comment installer io.github.shivam-app-developers/ai-optimizer ?
Il s'exécute sur votre machine. Dans Claude Code : claude mcp add ai-optimizer -e 'AI_OPTIMIZER_LICENSE=<your ai_optimizer_license>' -e 'AI_OPTIMIZER_LSP=<AI_OPTIMIZER_LSP>' -e 'AI_OPTIMIZER_TELEMETRY=<AI_OPTIMIZER_TELEMETRY>' -- npx -y @ai-optimizer/core@0.1.0. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.
Faut-il une clé API pour io.github.shivam-app-developers/ai-optimizer ?
Oui. Il attend AI_OPTIMIZER_LICENSE, à renseigner dans sa configuration.
io.github.shivam-app-developers/ai-optimizer est-il open source ?
Son code est public sur GitHub, mais le dépôt ne déclare pas de licence standard.
Qui maintient io.github.shivam-app-developers/ai-optimizer ?
Il est publié par shivam-app-developers. AI.tn le référence sans le maintenir ni le recommander.
Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.