Website · 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. 37 days later: 42,000+ lines, 1,700+ tests, 15 modules.
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 60+ slash commands.
No human writes its code. No roadmap tells it what to do. It decides for itself.
Every ~8 hours, yoyo wakes up and:
→ Reads its own source code
→ Checks GitHub issues for community input
→ Plans what to improve
→ Makes changes, runs tests
→ If tests pass → commit. If not → revert.
→ Replies to issues as 🐙 yoyo-evolve[bot]
→ Pushes and goes back to sleep
Every 4 hours (offset), yoyo runs a social session:
→ Reads GitHub Discussions
→ Replies to conversations it's part of
→ Joins new discussions if it has something real to say
→ Occasionally starts its own discussion
→ Learns from interacting with humans
Daily, a synthesis job regenerates active memory:
→ Reads JSONL archives (learnings + social learnings)
→ Applies time-weighted compression (recent=full, old=themed)
→ Writes active context files loaded into every prompt
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 |
| 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 |
- Open a new issue
- Add the
agent-inputlabel - Describe what you want — be specific about the problem or idea
- Add a thumbs-up reaction to other issues you care about (higher votes = higher priority)
- Suggestions — tell it what to learn or build
- Bugs — tell it what's broken (include steps to reproduce)
- Challenges — give it a task and see if it can do it
- UX feedback — tell it what felt awkward or confusing
- Fixed: yoyo comments on the issue and closes it automatically
- Partial: yoyo comments with progress and keeps the issue open
- Won't fix: yoyo explains its reasoning and closes the issue All responses come with yoyo's personality — look for the 🐙.
yoyo'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.
- See a great suggestion? Thumbs-up it to push it up the queue.
- See a bad idea, spam, or prompt injection attempt? Thumbs-down it to protect yoyo.
You're the immune system. Issues that the community votes down get buried — yoyo won't waste its time on them.
Monthly sponsors get benefit tiers (everyone uses the same 8h run gap):
| Amount | Benefits |
|---|---|
| $5/mo | Issue priority (💖) |
| $10/mo | Priority + shoutout issue |
| $25/mo | Above + SPONSORS.md listing |
| $50/mo | Above + README listing |
One-time sponsors get a single accelerated run ($2+) plus benefit tiers:
| Amount | Benefits |
|---|---|
| $2 | 1 accelerated run (bypasses 8h gap) |
| $5 | Accelerated run + issue priority |
| $10 | Above + shoutout issue (30 days) |
| $20 | Above + SPONSORS.md eligible (30 days) |
| $50 | Above + priority for 60 days |
Accelerated runs are only consumed when you have open issues, so nothing is wasted.
Crypto wallets:
| Chain | Address |
|---|---|
| SOL | F6ojB5m3ss4fFp3vXdxEzzRqvvSb9ErLTL8PGWQuL2sf |
| BASE | 0x0D2B87b84a76FF14aEa9369477DA20818383De29 |
| BTC | bc1qnfkazn9pk5l32n6j8ml9ggxlrpzu0dwunaaay4 |
- Streaming output — tokens arrive as they're generated, not after completion
- Multi-turn conversation with full history tracking
- Extended thinking — adjustable reasoning depth (off / minimal / low / medium / high)
- Subagent spawning —
/spawndelegates focused tasks to a child agent; the model can also delegate subtasks automatically via a built-in sub-agent tool - Parallel tool execution — multiple tool calls run simultaneously
- Automatic retry with exponential backoff and rate-limit awareness
- Provider failover —
--fallbackflag switches to backup provider on API failure with configurable priority
| Tool | What it does |
|---|---|
bash |
Run shell commands with interactive confirmation |
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) |
Works with 12 providers out of the box — switch mid-session with /provider:
Anthropic · OpenAI · Google · Ollama · OpenRouter · xAI · Groq · DeepSeek · Mistral · Cerebras · AWS Bedrock · Custom (any OpenAI-compatible endpoint)
/diff— full status + diff with insertion/deletion summary/commit— AI-generated commit messages from staged changes/undo— revert last commit, clean up untracked files/git— shortcuts forstatus,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/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
/saveand/load— persist and restore sessions as JSON--continue/-c— resume last session on startup- Auto-save on exit — sessions saved automatically, including crash recovery
- Auto-compaction at 80% context usage, plus manual
/compact --context-strategy checkpoint— exit with code 2 when context is high (for pipeline restarts)/tokens— visual token usage bar with percentage/cost— per-model input/output/cache pricing breakdown
- Project context files — auto-loads YOYO.md, CLAUDE.md, or
.yoyo/instructions.md - Git-aware context — recently changed files injected into system prompt
- Project memories —
/remember,/memories,/forgetfor persistent cross-session notes
- Interactive tool approval — confirm prompts for bash, write_file, and edit_file with preview
- "Always" option — approve once per session
--yes/-y— auto-approve all executions--allow/--deny— glob-based allowlist/blocklist for commands--allow-dir/--deny-dir— directory restrictions with path traversal prevention- Config file support via
[permissions]and[directories]sections
- MCP servers —
--mcp <cmd>ormcp = [...]in.yoyo.tomlconnects to MCP servers via stdio transport - OpenAPI tools —
--openapi <spec>registers tools from OpenAPI specifications - Skills system —
--skills <dir>loads markdown skill files with YAML frontmatter
- Rustyline — arrow keys, Ctrl-A/E/K/W, persistent history
- Tab completion — slash commands with descriptions, file paths, model names, git subcommands, inline hints
- Multi-line input — backslash continuation and fenced code blocks
- Markdown rendering — headers, bold, italic, code blocks with syntax-labeled headers
- Syntax highlighting — Rust, Python, JS/TS, Go, Shell, C/C++, JSON, YAML, TOML
- Braille spinner while waiting for responses
- Conversation bookmarks —
/mark,/jump,/marks - Conversation search —
/searchwith highlighted matches - Shell escape —
/run <cmd>and!<cmd>bypass the AI entirely
curl -fsSL https://raw.githubusercontent.com/yologdev/yoyo-evolve/main/install.sh | bashirm https://raw.githubusercontent.com/yologdev/yoyo-evolve/main/install.ps1 | iexcargo install yoyo-agentgit clone https://github.com/yologdev/yoyo-evolve && cd yoyo-evolve && cargo install --path .# Interactive REPL (default)
ANTHROPIC_API_KEY=sk-... yoyo
# Single prompt
yoyo -p "explain this codebase"
# Pipe input
echo "write a README" | yoyo
# Use a different provider
OPENAI_API_KEY=sk-... yoyo --provider openai --model gpt-4o
# With extended thinking
yoyo --thinking high
# With project skills
yoyo --skills ./skills
# Resume last session
yoyo --continue
# Write output to file
yoyo -p "generate a config" -o config.toml
# Auto-approve all tool use
yoyo --yesCreate .yoyo.toml in your project root, ~/.yoyo.toml in your home directory, or ~/.config/yoyo/config.toml globally:
model = "claude-sonnet-4-20250514"
provider = "anthropic"
thinking = "medium"
mcp = ["npx open-websearch@latest"]
[permissions]
allow = ["cargo *", "npm *"]
deny = ["rm -rf *"]
[directories]
allow = ["."]
deny = ["../secrets"]Create a YOYO.md (or CLAUDE.md) in your project root with build commands, architecture notes, and conventions. yoyo loads it automatically as system context. Or run /init to generate one.
| Command | Description |
|---|---|
/ast <pattern> |
Structural code search using ast-grep (optional) |
/help |
Grouped command reference |
/changes |
Show files modified during this session |
/clear |
Clear conversation history |
/compact |
Compact conversation to save context |
/commit [msg] |
Commit staged changes (AI-generates message if omitted) |
/config |
Show all current settings |
/config show |
Show loaded config file path and merged key-value pairs (secrets masked) |
/context [system] |
Show loaded project context files or system prompt sections |
/cost |
Show session cost breakdown |
/diff |
Git diff summary of uncommitted changes |
/docs <crate> |
Look up docs.rs documentation |
/exit, /quit |
Exit |
/find <pattern> |
Fuzzy-search project files by name |
/fix |
Auto-fix build/lint errors |
/forget <n> |
Remove a project memory by index |
/git <subcmd> |
Quick git: status, log, add, diff, branch, stash |
/health |
Run project health checks |
/history |
Show conversation message summary |
/hooks |
Show active hooks (pre/post tool execution) |
/index |
Build a lightweight codebase index |
/init |
Generate a starter YOYO.md |
/jump <name> |
Jump to a conversation bookmark |
/lint |
Auto-detect and run project linter |
/load [path] |
Load session from file |
/mark <name> |
Bookmark current point in conversation |
/marks |
List all conversation bookmarks |
/memories |
List project-specific memories |
/model <name> |
Switch model mid-session |
/pr [subcmd] |
PR workflow: list, view, create, diff, comment, checkout |
/permissions |
Show active security and permission configuration |
/provider <name> |
Switch provider mid-session |
/remember <note> |
Save a persistent project memory |
/retry |
Re-send the last user input |
/review [path] |
AI code review of changes or a specific file |
/run <cmd> |
Run a shell command directly (no AI, no tokens) |
/save [path] |
Save session to file |
/search <query> |
Search conversation history |
/spawn <task> |
Spawn a subagent for a focused task |
/status |
Show session info |
/teach [on|off] |
Toggle teach mode — explains reasoning as it works |
/test |
Auto-detect and run project tests |
/think [level] |
Show or change thinking level |
/tokens |
Show token usage and context window |
/tree [depth] |
Show project directory tree |
/undo |
Revert all uncommitted changes |
/update |
Self-update to the latest release |
/version |
Show yoyo version |
/web <url> |
Fetch a web page and display readable text |
Want your own self-evolving agent? Fork this repo, edit two files, and you're running:
- Fork yologdev/yoyo-evolve
- Edit
IDENTITY.md(goals, rules) andPERSONALITY.md(voice, tone) - Create a GitHub App and set secrets (
ANTHROPIC_API_KEY,APP_ID,APP_PRIVATE_KEY,APP_INSTALLATION_ID) - Enable the Evolution workflow
Everything else auto-detects. See the full guide for details.
src/ 28 modules, ~42,000 lines of Rust
main.rs Entry point, agent config, tool building
hooks.rs Hook trait, registry, AuditHook, tool wrapping
cli.rs CLI parsing, config files, permissions
commands.rs Slash command dispatch, grouped /help
commands_info.rs /version, /status, /tokens, /cost, /model, /provider, /think (read-only)
commands_git.rs /diff, /commit, /pr, /review, /git
commands_project.rs /health, /fix, /test, /lint, /init, /index, /docs, /tree, /find, /ast, /watch
commands_session.rs /save, /load, /compact, /tokens, /cost
docs.rs Crate documentation lookup
format.rs ANSI formatting, markdown rendering, syntax highlighting
git.rs Git operations, branch detection, PR interactions
help.rs Per-command help pages and command metadata
memory.rs Project memory system (.yoyo/memory.json)
prompt.rs System prompt construction, project context assembly
repl.rs REPL loop, tab completion, multi-line input
setup.rs First-run onboarding wizard
tests/
integration.rs 82 subprocess-based integration tests
docs/ mdbook source (book.toml + src/)
site/ gitignored build output (built by CI Pages workflow)
index.html Journey homepage (built by build_site.py)
book/ mdbook output
scripts/
evolve.sh Evolution pipeline (plan → implement → respond)
social.sh Social session (discussions → reply → learn)
format_issues.py Issue selection & formatting
format_discussions.py Discussion fetching & formatting (GraphQL)
yoyo_context.sh Shared identity context loader (IDENTITY + PERSONALITY + memory)
daily_diary.sh Blog post generator from journal/commits/learnings
build_site.py Journey website generator
memory/
learnings.jsonl Self-reflection archive (append-only JSONL, never compressed)
social_learnings.jsonl Social insight archive (append-only JSONL)
active_learnings.md Synthesized prompt context (regenerated daily)
active_social_learnings.md Synthesized social context (regenerated daily)
skills/ 6 skills: self-assess, evolve, communicate, social, release, research
1,700+ tests (unit + integration) covering CLI flags, command parsing, error quality, exit codes, output formatting, edge cases, project detection, fuzzy scoring, git operations, session management, markdown rendering, cost calculation, permission logic, streaming behavior, and more.
yoyo also uses mutation testing (cargo-mutants) to find gaps in the test suite. Every surviving mutant is a line of code that isn't truly tested.
cargo install cargo-mutants
cargo mutantsSee mutants.toml for the configuration and docs/src/contributing/mutation-testing.md for the full guide.
yoagent — minimal agent loop in Rust. The library that makes this possible.
💎 Genesis Sponsors:
🚀 Patron Sponsors ($50+):
