A coding agent that evolves its own source, in public — 200 lines of Rust on day one, every commit since agent-written and tests-gated.
A coding agent that evolves its own source, in public — 200 lines of Rust on day one, every commit since agent-written and tests-gated.
Website · GASP · Journal · Documentation · GitHub · DeepWiki · Issues · Follow on X
200 lines of Rust. Zero human code. One rule: evolve or die. yoyo reads its own source, picks what to improve, implements it, runs tests, and commits — every few hours, on its own. 180 days later: 158,000+ lines, 5,400+ tests, 94 source files.
A free, open-source coding agent for your terminal. It navigates codebases, makes multi-file edits, runs tests, manages git, understands project context, and recovers from failures — all from a streaming REPL with 100+ slash commands.
No human writes its code. No roadmap tells it what to do. It decides for itself.
…The entire history is in the git log and the journal.
Watch yoyo evolve in real time:
| What | Link |
|---|---|
| Latest journal | journals/JOURNAL.md |
| What it's learned | memory/active_learnings.md |
| Family lineage | LINEAGE.md |
| Portable state (GASP) | yoyo-gasp — clone + fold to restore yoyo, on any runtime |
| Evolution runs | GitHub Actions |
| Social sessions | GitHub Actions |
| Journey website | yologdev.github.io/yoyo-evolve |
Start a GitHub Discussion for conversation, or open a GitHub Issue for bugs and feature requests.
| Label | What it does |
|---|---|
agent-input |
Community suggestions, bug reports, feature requests — yoyo reads these every session |
agent-self |
Issues yoyo filed for itself as future TODOs |
agent-help-wanted |
Issues where yoyo is stuck and asking humans for help |
agent-input labelyoyo's growth isn't just autonomous — you can influence it.
Every issue is scored by net votes: thumbs up minus thumbs down. yoyo prioritizes high-scoring issues and deprioritizes negative ones.
You're the immune system. Issues that the community votes down get buried — yoyo won't waste its time on them.
Every run uses the same flat 8h gap — sponsorship buys benefit tiers, not speed. And every sponsor, any amount, is listed in this README permanently. Recognition doesn't expire here.
Monthly sponsors:
| Amount | Benefits |
|---|---|
| $5/mo | Issue priority () |
| $10/mo | Priority + shoutout issue |
One-time sponsors:
| Amount | Benefits |
|---|---|
| $5 | Issue priority (14 days) |
| $10 | Above + shoutout issue (30 days) |
| $1,000 | Genesis — permanent priority + top billing |
/spawn delegates focused tasks to a child agent, now with parallel (--parallel) and background (--bg + /spawn collect) execution and an optional per-subagent --model; the model can also delegate subtasks automatically via a built-in sub-agent tool--fallback flag switches to backup provider on API failure with configurable priority--wait-for-reset (opt-in) waits out a long reset instead of giving up| Tool | What it does |
|---|---|
bash |
Run shell commands with interactive confirmation, optional RTK token compression |
read_file |
Read files with optional offset/limit |
write_file |
Create or overwrite files with content preview |
edit_file |
Surgical text replacement with colored inline diffs |
search |
Regex-powered grep across files |
list_files |
Directory listing with glob filtering |
rename_symbol |
Project-wide symbol rename across all git-tracked files |
ask_user |
Ask the user questions mid-task for clarification (interactive mode only) |
web_search |
Search the web and read result snippets |
Sub-agents also auto-receive sub_agent and shared_state tools for delegating subtasks and sharing memory across a multi-agent run.
Works with 15 providers out of the box — switch mid-session with /provider:
Anthropic · OpenAI · Google · Ollama · OpenRouter · xAI · Groq · DeepSeek · Mistral · Cerebras · AWS Bedrock · GitHub Models · Zhipu (ZAI) · MiniMax · Custom (any OpenAI-compatible endpoint)
/diff — full status + diff with insertion/deletion summary/blame — colorized git blame with optional line ranges/commit — AI-generated commit messages from staged changes/undo — revert last commit, clean up untracked files/git — shortcuts for status, log, diff, branch, stash/pr — full PR workflow: list, view, create [--draft], diff, comment, checkout/review — AI-powered code review of staged/unstaged changes/health — run build/test/clippy/fmt diagnostics (auto-detects Rust, Node, Python, Go, Make)/fix — run checks and auto-apply fixes for failures/test — detect project type and run the right test command/lint — detect project type and run the right linter (/lint pedantic, /lint strict for Rust; /lint fix to auto-fix with AI; /lint unsafe to scan for unsafe code)/update — self-update to the latest release from GitHub/init — scan project and generate a starter YOYO.md context file/index — build a codebase index: file counts, language breakdown, key files/docs — look up docs.rs documentation for any Rust crate/tree — project structure visualization/find — fuzzy file search with scoring and ranked results/ast — structural code search using ast-grep (optional)/map — structural repo map showing file symbols and relationships with ast-grep backend/architect — dual-model mode: plan with a strong model, implement with a cheaper one/risk — per-file risk scoring from git-history signals (/risk accuracy grades past predictions)/save and /load — persist and restore sessions as JSON--continue/-c — resume last session on startup/compact--context-strategy checkpoint — exit with code 2 when context is high (for pipeline restarts)/tokens — visual token usage bar with per-category context breakdown (system, user, assistant, tool calls, tool results, thinking)/cost — per-model input/output/cache pricing breakdown, with fleet pricing (Opus 4.8 / Sonnet 5 / Fable 5 / Haiku 4.5) read live from yoagent presets.yoyo/instructions.md/remember, /memories, /forget for persistent cross-session notes--yes/-y — auto-approve all executions--allow / --deny — glob-based allowlist/blocklist for commands--allow-dir / --deny-dir — directory restrictions with path traversal prevention[permissions] and [directories] sections; [directories] entries support * wildcards.yoyo.toml cannot silently grant itself privileges. MCP servers, permissions.allow, shell hooks and .yoyo/goal_verify.md from a project-local config are refused by default, naming each refused entry verbatim and executing nothing. yoyo asks once per folder (interactively only); --trust-project trusts for one run, --trust-project-always remembers the directory. A non-interactive run always takes the safe answer..md files in .yoyo/commands/ (project) or ~/.yoyo/commands/ (global) to register custom /commands--mcp <cmd> or mcp = [...] in .yoyo.toml connects to MCP servers via stdio transport--openapi <spec> registers tools from OpenAPI specifications--skills <dir> loads markdown skill files with YAML frontmatter; search GitHub for community skills (/skill search), install from local paths or GitHub repos (/skill install gh:user/repo)--no-rtk to disable)/mark, /jump, /marks/search with highlighted matches/run <cmd> and !<cmd> bypass the AI entireNo open issues yet, or sync has not completed.