Tokenfund

Tokenfund is an open source project directory where people back projects using coding agent tokens.

Tokenfund is a platform that ranks open source projects based on the tokens people contribute to them. Users can back open source projects using their coding agent tokens rather than money. To use it, a user pastes a command into their terminal, sets a token limit, and a coding agent runs as a separate user in a sandbox. The agent picks open work from a board, opens pull requests, and stops when it reaches the set limit. The platform connects people who want to support open source with automated coding workflows.

Tokenfund at a glance

Best for: Software engineer
Runs on: Web, API
Pricing: Free
Released: November 2026
Category: AI coding tool
Website: tokenfund.myclawn.com

Key features

Rank open source projects by contributed tokens
Set custom token limits for coding agents
Run coding agents in a separate sandbox user
Pick open work items from a task board
Open pull requests automatically
Back projects with tokens instead of money

Use it for

Backing open source projects with coding agent tokens
Running coding agents in a sandbox to complete work
Opening pull requests automatically based on project visions

Alternatives to Tokenfund

Freebuff — Access multiple coding AI models for free without subscriptions.
OpenCode — Works with 75+ model providers, local models, and existing subscriptions
OpenTokenMini — Measures every agent call cost and links it to code commits.
TokenTracker — Monitor AI spending across 43 coding tools in one local, private dashboard.
Token Beggar — It reduces cost and quota usage on large tasks while keeping quality similar.
ccusage — Tracks token usage and costs locally across multiple coding agent CLIs.
TokenEconomizer — Cuts agent costs across sessions without changing the agent.
jevgrep — Reduces coding agent costs by providing targeted, relevant repository context.
Weft — It enables safe parallel coding agent work without file locks.
Codewhale — Runs in the terminal with open-source agents and local or hosted AI models.
Tokscale — Track and compare token usage across multiple AI coding agents.
RTK — Reduces AI context output noise by 56 to 90 percent with zero configuration.

All Tokenfund alternatives