Conifer
Conifer is a routing layer and harness for AI-assisted development that dynamically selects the model, provider, and cache for each query at arrival time. It works across major coding interfaces including Claude Desktop, Codex Desktop, Cursor, VS Code, and the terminal, and can run fully on-device when privacy is a priority. Cloud tokens bill at the model's own rate with no markup, while local inference through any llama-compatible endpoint costs nothing.
- Developer Tools
- Artificial Intelligence
- Software Only
Funding
Raised to date
$500KRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
Founders
Founder details are not available yet.
Product
Problem
Developers using AI coding assistants often face a fragmented landscape of models, providers, and tools, each with different costs, latency, and capabilities. Manually selecting the right model for each query is inefficient, and cloud inference can impose significant token costs even when local hardware would suffice.
Solution
Conifer is a routing layer and harness for AI-assisted development that dynamically selects the model, provider, and cache for each query at arrival time. Users send plain text prompts, and Conifer handles the underlying infrastructure decisions, routing to cloud models at their own rate with no markup, or to local inference through any llama-compatible endpoint at no cost. The platform works across major coding interfaces including Claude Desktop, Codex Desktop, Cursor, VS Code, and the terminal, and can run fully on-device when privacy is a priority. Conifer also offers a gateway with access to over 200 models, and supports bring-your-own provider keys for maximum flexibility.
Target Audience
Primary users are software developers and engineering teams who use AI coding assistants and want to lower inference costs, improve response quality through smart routing, and maintain control over where their code and prompts are processed.
Features
- Dynamic query-based routing that selects the harness, model, provider, and cache per query in real time
- Cloud token billing at the model's base rate with zero markup on top
- Free local inference via any llama-compatible endpoint or Conifer's own engine, requiring no per-token cost
- Integration with leading development tools: Claude Desktop, Codex Desktop, Antigravity, Terminal, cmux, VS Code, OpenCode, Pi, Zed, and Cursor
- Privacy-first architecture: prompts and responses stay on-device for local turns; cloud turns expose only the necessary context to the selected provider; text sampling is off by default and usage telemetry carries no text content
- Cookieless first-party analytics with a daily-rotating hash for visitor counting, with no third-party analytics or advertising networks