UNPKG

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
{ "$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": [] } }