lynkr
Version:
Self-hosted LLM gateway and tier-routing proxy for Claude Code, Cursor, and Codex. Routes across Ollama, AWS Bedrock, OpenRouter, Databricks, Azure OpenAI, llama.cpp, and LM Studio with prompt caching, MCP tools, and 60-80% cost savings.
111 lines (105 loc) • 4.43 kB
JSON
{
"$schema": "https://fundingjson.org/schema/v1.1.0.json",
"version": "v1.1.0",
"entity": {
"type": "individual",
"role": "maintainer",
"name": "Vishal Veera Reddy",
"email": "veerareddyvishal56@gmail.com",
"description": "Indian software engineer building open-source AI infrastructure. Sole maintainer of Lynkr, a self-hosted AI gateway that lets developers run any AI coding tool on any LLM provider.",
"webpageUrl": {
"url": "https://github.com/vishalveerareddy123"
}
},
"projects": [
{
"guid": "lynkr",
"name": "Lynkr",
"description": "A self-hosted AI gateway that decouples AI coding tools (Claude Code, Cursor, Codex, Cline, jcode, Pi) from their default LLM providers. Lynkr auto-detects the connecting tool, translates between Anthropic and OpenAI request formats, and routes to any of 12+ backends (Ollama, AWS Bedrock, Azure OpenAI, OpenRouter, Databricks, Moonshot, Google Vertex, llama.cpp, LM Studio, and more). A request-complexity classifier sends simple turns to free local models and complex ones to flagship cloud models, cutting per-developer AI bills 60-80% while removing vendor lock-in. Includes tool-result compression, MCP Code Mode (96% token reduction on tool definitions), persistent memory, and tier-based routing — all configured through a single .env file.",
"webpageUrl": {
"url": "https://fast-editor.github.io/Lynkr/"
},
"repositoryUrl": {
"url": "https://github.com/Fast-Editor/Lynkr"
},
"licenses": ["spdx:Apache-2.0"],
"tags": [
"ai",
"ai-gateway",
"llm",
"llm-router",
"developer-tools",
"proxy",
"claude-code",
"ollama",
"anthropic",
"openai"
]
}
],
"funding": {
"channels": [
{
"guid": "github-sponsors",
"type": "payment-provider",
"address": "https://github.com/sponsors/vishalveerareddy123",
"description": "Support Lynkr development via GitHub Sponsors."
},
{
"guid": "fossunited-grant",
"type": "other",
"address": "grants@fossunited.org",
"description": "FOSS United Foundation grant channel for institutional FOSS funding."
},
{
"guid": "bank-transfer",
"type": "bank",
"address": "Available on request via the project email.",
"description": "Direct bank transfer for organisations or grant disbursements."
}
],
"plans": [
{
"guid": "core-maintenance-2026",
"status": "active",
"name": "Core maintenance + roadmap (12 months)",
"description": "Funds full-time work on Lynkr's core gateway: provider-format conversions, tier routing, tool-call translation across 10+ model formats (Minimax, Qwen, GLM, Llama, DeepSeek, Mistral), tool-result compression, persistent memory, MCP Code Mode, observability, tests, and docs. Estimated cost reflects one Indian maintainer working full-time for a year.",
"amount": 500000,
"currency": "INR",
"frequency": "yearly",
"channels": ["fossunited-grant", "bank-transfer"]
},
{
"guid": "infra-2026",
"status": "active",
"name": "Infrastructure + benchmarks",
"description": "Funds CI runners, benchmark harness for cost/quality/latency comparisons across providers, public dashboard at lynkr.dev, and self-hosted SearXNG + telemetry mirrors used by Lynkr's web search and routing layers.",
"amount": 150000,
"currency": "INR",
"frequency": "yearly",
"channels": ["fossunited-grant", "bank-transfer"]
},
{
"guid": "community-sponsor",
"status": "active",
"name": "Community sponsorship",
"description": "Recurring small-amount sponsorship from individual developers and small teams who use Lynkr.",
"amount": 0,
"currency": "USD",
"frequency": "monthly",
"channels": ["github-sponsors"]
},
{
"guid": "one-time",
"status": "active",
"name": "One-time contribution",
"description": "Any-amount one-time contribution from users or supporters.",
"amount": 0,
"currency": "USD",
"frequency": "one-time",
"channels": ["github-sponsors", "bank-transfer"]
}
],
"history": []
}
}