87.6% fewer tokens on JSON tool results. 53% fewer tokens on tool-heavy requests. 171ms semantic cache hits. Zero code changes.
npm version Tests License: Apache 2.0 Node.js Ask DeepWiki
JSON Compression 53%
Tool Token Reduction 171ms
Semantic Cache Hits 13+
LLM Providers 0
Code Changes Required
Numbers from a live benchmark against LiteLLM on identical workloads. See full report →
npm install -g lynkr
First run creates a .env file. Edit it with your provider settings.
Option A: Free & Local (Ollama) - Recommended for Testing
# Install Ollama first: https://ollama.com
ollama pull qwen2.5-coder:latestCreate/edit .env in your project directory:
# Provider MODEL_PROVIDER=ollama FALLBACK_ENABLED=false # Ollama Configuration OLLAMA_ENDPOINT=http://localhost:11434 OLLAMA_MODEL=qwen2.5-coder:latest # Server PORT=8081 # Optional: Limits (remove for unlimited) POLICY_MAX_STEPS=50 POLICY_MAX_TOOL_CALLS=100 # Disable overly strict command filtering POLICY_SAFE_COMMANDS_ENABLED=false
Option B: Cloud (OpenRouter) - Recommended for Production
# Get API key from https://openrouter.aiCreate/edit .env:
# Provider MODEL_PROVIDER=openrouter OPENROUTER_API_KEY=sk-or-v1-your-key-here FALLBACK_ENABLED=false # Server PORT=8081 # Optional: Limits (remove for unlimited) POLICY_MAX_STEPS=50 POLICY_MAX_TOOL_CALLS=100 # Optional: Enable caching PROMPT_CACHE_ENABLED=true SEMANTIC_CACHE_ENABLED=true
Option C: Enterprise (AWS Bedrock)
Create/edit .env:
# Provider MODEL_PROVIDER=bedrock AWS_BEDROCK_API_KEY=your-aws-key AWS_BEDROCK_MODEL_ID=anthropic.claude-3-5-sonnet-20241022-v2:0 FALLBACK_ENABLED=false # Server PORT=8081 # Optional: Limits (remove for unlimited) POLICY_MAX_STEPS=50 POLICY_MAX_TOOL_CALLS=100
Option D: Enterprise (Databricks)
Create/edit .env:
# Provider MODEL_PROVIDER=databricks DATABRICKS_API_BASE=https://your-workspace.cloud.databricks.com DATABRICKS_API_KEY=your-token FALLBACK_ENABLED=false # Server PORT=8081 # Optional: Limits (remove for unlimited) POLICY_MAX_STEPS=50 POLICY_MAX_TOOL_CALLS=100
Then start Lynkr:
lynkr start
Claude Code
Windows (Command Prompt):
set ANTHROPIC_BASE_URL=http://localhost:8081 set ANTHROPIC_API_KEY=dummy claude "write a hello world in python"
Linux/macOS:
export ANTHROPIC_BASE_URL=http://localhost:8081 export ANTHROPIC_API_KEY=dummy claude "write a hello world in python"
Cursor IDE
- Settings → Models → Override Base URL
- Set to:
http://localhost:8081/v1 - API Key:
any-value
Codex CLI
Edit ~/.codex/config.toml:
model_provider = "lynkr" [model_providers.lynkr] base_url = "http://localhost:8081/v1" wire_api = "responses"
✅ Done! Your AI tool now uses your chosen provider.
Problem: You're running an older version (< 9.3.0).
Solution: Update to the latest version:
npm install -g lynkr@latest
If you must use an older version, set NODE_ENV=production before starting.
This is just a warning - you can ignore it. Tier routing is optional.
To remove the warning, add to .env:
TIER_SIMPLE=ollama:qwen2.5-coder:latest TIER_MEDIUM=ollama:qwen2.5-coder:latest TIER_COMPLEX=ollama:qwen2.5-coder:latest TIER_REASONING=ollama:qwen2.5-coder:latest
Solution: Add to .env:
FALLBACK_ENABLED=false
Problem: Ollama is not running.
Solution:
ollama serve
Keep this terminal open, and start Lynkr in a new terminal.
Problem: Lynkr is not running or wrong port.
Solution: Check Lynkr is running on the correct port:
curl http://localhost:8081/
Should return: {"service":"Lynkr","version":"9.x.x","status":"running"}
AI coding tools lock you into one provider and send every token raw. Lynkr breaks both locks.
Claude Code / Cursor / Codex / Cline / Continue
↓
Lynkr
┌─────────────────────┐
│ Strip unused tools │ ← 53% fewer tokens on tool calls
│ Compress JSON blobs │ ← 87.6% on large tool results
│ Semantic cache │ ← 171ms hits, 0 tokens billed
│ Route by complexity │ ← cheap model for simple, cloud for hard
└─────────────────────┘
↓
Ollama | Bedrock | Azure | Moonshot | OpenRouter | OpenAI
What you get:
- ✅ 53% fewer tokens on tool-heavy requests (Claude Code, Cursor sessions)
- ✅ 87.6% compression on large JSON tool results (grep, file reads, test output)
- ✅ Semantic cache serves repeated queries in 171ms with 0 tokens billed
- ✅ Automatic tier routing — simple questions go to cheap models, complex ones escalate
- ✅ Route through your company's infrastructure (Databricks, Azure, Bedrock)
- ✅ Zero code changes — just change one environment variable
| Provider | Type | Example Models | Cost |
|---|---|---|---|
| Ollama | Local | qwen2.5-coder, deepseek-coder, llama3 | Free |
| llama.cpp | Local | Any GGUF model | Free |
| LM Studio | Local | Local models with GUI | Free |
| OpenRouter | Cloud | GPT-4o, Claude 3.5, Llama 3, Gemini | $ |
| AWS Bedrock | Cloud | Claude, Llama, Mistral, Titan | $$ |
| Databricks | Cloud | Claude Sonnet 4.5, Opus 4.6 | $$$ |
| Azure OpenAI | Cloud | GPT-4o, o1, o3 | $$$ |
| Azure Anthropic | Cloud | Claude Sonnet, Opus | $$$ |
| OpenAI | Cloud | GPT-4o, o3-mini | $$$ |
| DeepSeek | Cloud | DeepSeek R1, Reasoner | $ |
4 local providers for 100% offline, free usage. 10+ cloud providers for scale.
Route different request types to different models automatically:
# .env file MODEL_PROVIDER=ollama FALLBACK_ENABLED=false # Use small/fast models for simple tasks TIER_SIMPLE=ollama:qwen2.5:3b # Use medium models for normal coding TIER_MEDIUM=ollama:qwen2.5:7b # Use powerful models for complex architecture TIER_COMPLEX=ollama:deepseek-r1:14b TIER_REASONING=ollama:deepseek-r1:14b # Optional: Limits (remove for unlimited) for long conversations POLICY_MAX_STEPS=50 POLICY_MAX_TOOL_CALLS=100
Lynkr analyzes each request and routes it to the appropriate tier. Simple questions use fast models. Complex refactoring uses powerful models.
Result: 70-90% of requests use cheaper/faster models. Only hard problems hit expensive models.
Copy-paste ready configuration for immediate use:
# .env - Minimal Ollama Setup # ============================================ # REQUIRED: Provider Configuration # ============================================ MODEL_PROVIDER=ollama FALLBACK_ENABLED=false # ============================================ # REQUIRED: Ollama Settings # ============================================ OLLAMA_ENDPOINT=http://localhost:11434 OLLAMA_MODEL=qwen2.5-coder:latest # ============================================ # REQUIRED: Server Configuration # ============================================ PORT=8081 HOST=0.0.0.0 # ============================================ # REQUIRED: Claude Code/Cursor Compatibility # ============================================ POLICY_MAX_STEPS=50 POLICY_MAX_TOOL_CALLS=100 POLICY_SAFE_COMMANDS_ENABLED=false # ============================================ # OPTIONAL: Performance (Recommended) # ============================================ LOG_LEVEL=warn LOAD_SHEDDING_ENABLED=true LOAD_SHEDDING_HEAP_THRESHOLD=0.85
Steps:
- Install Ollama:
curl -fsSL https://ollama.com/install.sh | sh - Pull model:
ollama pull qwen2.5-coder:latest - Copy above to
.envin your project directory - Run:
lynkr start
Optimized for cost savings with smart routing:
# .env - Production OpenRouter Setup # ============================================ # REQUIRED: Provider Configuration # ============================================ MODEL_PROVIDER=openrouter OPENROUTER_API_KEY=sk-or-v1-your-key-here FALLBACK_ENABLED=false # ============================================ # REQUIRED: Server Configuration # ============================================ PORT=8081 HOST=0.0.0.0 # ============================================ # TIER ROUTING: Smart Cost Optimization # ============================================ # Simple queries → Cheap/fast model TIER_SIMPLE=openrouter:google/gemini-flash-1.5 # Normal coding → Balanced model TIER_MEDIUM=openrouter:anthropic/claude-3.5-sonnet # Complex refactoring → Powerful model TIER_COMPLEX=openrouter:anthropic/claude-opus-4 # Deep reasoning → Most capable model TIER_REASONING=openrouter:anthropic/claude-opus-4 # ============================================ # REQUIRED: Claude Code/Cursor Compatibility # ============================================ POLICY_MAX_STEPS=50 POLICY_MAX_TOOL_CALLS=100 POLICY_SAFE_COMMANDS_ENABLED=false # ============================================ # OPTIONAL: Token Optimization (60-80% savings) # ============================================ PROMPT_CACHE_ENABLED=true SEMANTIC_CACHE_ENABLED=true SEMANTIC_CACHE_THRESHOLD=0.95 TOOL_INJECTION_ENABLED=false # ============================================ # OPTIONAL: Performance Tuning # ============================================ LOG_LEVEL=warn LOAD_SHEDDING_ENABLED=true LOAD_SHEDDING_HEAP_THRESHOLD=0.85
Expected savings: 70-90% of requests use Gemini Flash (
For teams using Databricks Model Serving:
# .env - Enterprise Databricks Setup # ============================================ # REQUIRED: Provider Configuration # ============================================ MODEL_PROVIDER=databricks DATABRICKS_API_BASE=https://your-workspace.cloud.databricks.com DATABRICKS_API_KEY=dapi1234567890abcdef FALLBACK_ENABLED=false # ============================================ # REQUIRED: Model Configuration # ============================================ # Option 1: Single model (no tier routing) DATABRICKS_MODEL=databricks-meta-llama-3-1-405b-instruct # Option 2: Tier routing (comment out above, uncomment below) # TIER_SIMPLE=databricks:databricks-meta-llama-3-1-70b-instruct # TIER_MEDIUM=databricks:databricks-claude-sonnet-4-5 # TIER_COMPLEX=databricks:databricks-claude-opus-4-6 # TIER_REASONING=databricks:databricks-claude-opus-4-6 # ============================================ # REQUIRED: Server Configuration # ============================================ PORT=8081 HOST=0.0.0.0 # ============================================ # REQUIRED: Claude Code/Cursor Compatibility # ============================================ POLICY_MAX_STEPS=50 POLICY_MAX_TOOL_CALLS=100 POLICY_SAFE_COMMANDS_ENABLED=false # ============================================ # OPTIONAL: Enterprise Features # ============================================ LOG_LEVEL=info LOAD_SHEDDING_ENABLED=true LOAD_SHEDDING_HEAP_THRESHOLD=0.85 # Optional: Metrics for monitoring # PROMETHEUS_METRICS_ENABLED=true
Use free Ollama, fallback to cloud when needed:
# .env - Hybrid Setup (Advanced) # ============================================ # PRIMARY: Local Ollama # ============================================ MODEL_PROVIDER=ollama OLLAMA_ENDPOINT=http://localhost:11434 OLLAMA_MODEL=qwen2.5-coder:latest # ============================================ # FALLBACK: Cloud Provider # ============================================ FALLBACK_ENABLED=true FALLBACK_PROVIDER=openrouter OPENROUTER_API_KEY=sk-or-v1-your-key-here # ============================================ # TIER ROUTING: Mix Local + Cloud # ============================================ TIER_SIMPLE=ollama:qwen2.5:3b TIER_MEDIUM=ollama:qwen2.5:7b TIER_COMPLEX=openrouter:anthropic/claude-3.5-sonnet TIER_REASONING=openrouter:anthropic/claude-opus-4 # ============================================ # REQUIRED: Server Configuration # ============================================ PORT=8081 HOST=0.0.0.0 # ============================================ # REQUIRED: Claude Code/Cursor Compatibility # ============================================ POLICY_MAX_STEPS=50 POLICY_MAX_TOOL_CALLS=100 POLICY_SAFE_COMMANDS_ENABLED=false # ============================================ # OPTIONAL: Performance # ============================================ LOG_LEVEL=warn LOAD_SHEDDING_ENABLED=true
Best of both worlds: 80% of requests stay local (free). Complex tasks use cloud (paid).
| Issue | Solution |
|---|---|
| "Service temporarily overloaded" | Ollama model too large for RAM. Use smaller model or increase --max-old-space-size |
| "Route not found: HEAD /" | Ignore - harmless health check from Claude Code |
| "Hallucinated tool calls" | Normal - Lynkr automatically filters invalid tools |
| "Safe Command DSL blocked" | Add POLICY_SAFE_COMMANDS_ENABLED=false to .env |
| "spawn graphify ENOENT" | Optional feature. Set CODE_GRAPH_ENABLED=false in .env (see Advanced Features section for installation) |
| Slow first request (20+ sec) | Ollama loading model into memory. Add OLLAMA_KEEP_ALIVE=30m in Ollama config |
| No response after N turns | Remove POLICY_MAX_STEPS and POLICY_MAX_TOOL_CALLS from .env (unlimited by default in v9.3.0+) |
# Enable all optimizations
PROMPT_CACHE_ENABLED=true
SEMANTIC_CACHE_ENABLED=true
TOOL_INJECTION_ENABLED=false
CODE_MODE_ENABLED=trueAlways-on (no config): smart tool selection (server mode), RTK tool-result compression (test/git/grep/lint/build/JSON output), MCP tool dedup (drops built-in WebSearch/WebFetch when an Exa/Tavily MCP tool is present), and request bypass (Claude CLI Warmup / title-extraction calls are answered locally, never hitting a provider).
Optional terse-output mode to cut output tokens:
CAVEMAN_ENABLED=true # off by default — nudges the model to be concise CAVEMAN_LEVEL=lite # lite | full | ultra
Per-request cost is computed from a model-pricing registry (LiteLLM → models.dev,
cached 24h) and recorded in telemetry. Models the registry doesn't know record
cost_usd=null (logged once) rather than a fabricated price. Pin prices for
unknown models:
# Per-1M-token USD prices, JSON keyed by model name MODEL_PRICE_OVERRIDES={"my-model":{"input":0.5,"output":1.5}}
MEMORY_ENABLED=true
MEMORY_TTL=3600000 # 1 hourLOAD_SHEDDING_ENABLED=true LOAD_SHEDDING_HEAP_THRESHOLD=0.85
curl -X POST http://localhost:8081/v1/admin/reload
Graphify provides AST-based code analysis for smarter routing decisions.
Installation (Rust required):
# Install Rust if not already installed curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh source $HOME/.cargo/env # Build and install graphify git clone https://github.com/safishamsi/graphify cd graphify cargo build --release sudo cp target/release/graphify /usr/local/bin/ # Verify installation graphify --version
Enable in .env:
CODE_GRAPH_ENABLED=true
CODE_GRAPH_WORKSPACE=/path/to/your/project # Optional, defaults to cwdFeatures:
- AST-based complexity scoring
- Structural code analysis (19 languages supported)
- Enhanced routing decisions based on code structure
Note: Graphify is completely optional. If not installed, Lynkr falls back to simpler complexity analysis.
NPM (recommended)
npm install -g lynkr
One-line installer
curl -fsSL https://raw.githubusercontent.com/Fast-Editor/Lynkr/main/install.sh | bashHomebrew (macOS / Linux)
brew tap fast-editor/lynkr brew install lynkr lynkr --version
Upgrade later with brew update && brew upgrade lynkr. The formula tracks the latest lynkr npm release automatically.
Docker
git clone https://github.com/Fast-Editor/Lynkr.git
cd Lynkr
docker-compose up -dFrom source
git clone https://github.com/Fast-Editor/Lynkr.git
cd Lynkr
npm install
cp .env.example .env
npm start| Guide | Description |
|---|---|
| Installation | All installation methods |
| Provider Setup | Configuration for all 12+ providers |
| Claude Code | Claude Code CLI integration |
| Cursor IDE | Cursor setup + troubleshooting |
| Codex CLI | Codex configuration |
| Tier Routing | Smart model routing by complexity |
| Token Optimization | 60-80% cost reduction |
| Troubleshooting | Common issues and solutions |
| API Reference | REST API endpoints |
| Production | Enterprise deployment |
Head-to-head against LiteLLM on the same backends (Ollama minimax-m2.5, Moonshot, Azure OpenAI), 9 scenarios across 4 feature categories. Apples-to-apples comparison is Lynkr vs LiteLLM billed tokens on the same scenario. Run with node benchmark-tier-routing.js.
Run: June 5, 2026 · Lynkr v9.3.2 · LiteLLM v1.87.1 · macOS, Apple Silicon.
| Mechanism | Lynkr | LiteLLM | Result |
|---|---|---|---|
| Smart tool selection (14 tools) | 959 tokens · 0ドル.0044 | 2,085 tokens · 0ドル.0091 | 53% fewer tokens, 52% cheaper |
| TOON compression (60-item grep JSON) | 427 tokens · 0ドル.009 | 3,458 tokens · 0ドル.018 | 87.6% fewer tokens, 50% cheaper |
Lynkr strips irrelevant tool schemas (smart tool selection) and binary-compresses large JSON tool results (TOON) — both in-process, no added latency.
| Tokens billed | Response time | |
|---|---|---|
| First call (cold) | 2,857 | 1,891ms |
| Second call — paraphrased, cache hit | 0 (served from cache) | 171ms (×ばつ faster) |
Near-identical prompts return cached responses in 171ms. Zero model tokens billed on a cache hit.
| Request | Lynkr routes to | LiteLLM routes to |
|---|---|---|
| "What does git stash do?" | minimax-m2.5 (local, free) |
Ollama (local) |
| JWT vs cookies security analysis | moonshot (cloud — correct) |
Ollama (local — wrong call) |
Lynkr scores each request on 15 dimensions (token count, code complexity, reasoning markers, risk signals, agentic patterns) and escalates automatically. LiteLLM's cost-based-routing sends everything to the cheapest model regardless of complexity.
| Monthly cost | vs LiteLLM | |
|---|---|---|
| LiteLLM | ~818ドル | baseline |
| Lynkr | ~409ドル | ~50% cheaper |
Based on a tool-heavy agentic session (TOON scenario). On equal footing — same provider, same model — Lynkr is cheaper due to token optimization.
→ Full benchmark report with methodology
| Scenario | Direct Anthropic | Lynkr + Ollama | Lynkr + OpenRouter |
|---|---|---|---|
| Daily coding (8h) | 10ドル-30/day | 0ドル (free) | 2ドル-8/day |
| Monthly (heavy use) | 300ドル-900 | 0ドル | 60ドル-240 |
With tier routing + token optimization: additional 50-87% savings on cloud providers depending on workload.
| Feature | Lynkr | LiteLLM | OpenRouter | PortKey |
|---|---|---|---|---|
| Setup | npm install -g lynkr |
Python + Docker + Postgres | Account signup | Docker stack |
| Claude Code native | ✅ Drop-in | ❌ | ||
| Cursor native | ✅ Drop-in | ❌ | ||
| Local models | Ollama, llama.cpp, LM Studio | Ollama only | ❌ | ❌ |
| Automatic tier routing | ✅ 15-dimension scorer | ❌ | ❌ Manual metadata | |
| TOON JSON compression | ✅ up to 87.6% | ❌ | ❌ | ❌ |
| Smart tool selection | ✅ up to 60% token reduction | ❌ | ❌ | ❌ |
| Semantic cache | ✅ 171ms hits, 0 tokens | ❌ | ❌ | ✅ Prompt cache only |
| Long-term memory | ✅ SQLite, per-session | ❌ | ❌ | ❌ |
| MCP integration | ✅ + Code Mode (96% reduction) | ❌ | ❌ | ❌ |
| Self-hosted | ✅ Node.js only | ✅ Python stack | ❌ SaaS | ✅ Docker |
| Dependencies | Node.js 20+ | Python, Prisma, PostgreSQL | None | Docker, Python |
Lynkr's edge: Purpose-built for AI coding tools. Compresses tokens before they reach the model — not just after. Zero-config for Claude Code, Cursor, and Codex. Installs in one command.
- GitHub Discussions — Ask questions
- Report Issues — Bug reports
- NPM Package — Official releases
- DeepWiki — AI-powered docs
Apache 2.0 — See LICENSE.
Built by Vishal Veera Reddy for developers who want control over their AI tools.