{"id":47727467,"url":"https://github.com/avala-ai/agent-code","last_synced_at":"2026-05-04T10:05:27.727Z","repository":{"id":348348700,"uuid":"1197589897","full_name":"avala-ai/agent-code","owner":"avala-ai","description":"An AI-powered coding agent for the terminal, written in pure Rust","archived":false,"fork":false,"pushed_at":"2026-04-29T04:12:18.000Z","size":1946,"stargazers_count":12,"open_issues_count":1,"forks_count":3,"subscribers_count":2,"default_branch":"main","last_synced_at":"2026-04-29T06:19:00.399Z","etag":null,"topics":["coding-agent"],"latest_commit_sha":null,"homepage":"http://avala-ai.github.io/agent-code/","language":"Rust","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/avala-ai.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":"CODEOWNERS","security":"SECURITY.md","support":null,"governance":null,"roadmap":"ROADMAP.md","authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-03-31T17:51:18.000Z","updated_at":"2026-04-29T04:12:20.000Z","dependencies_parsed_at":"2026-04-07T01:00:43.632Z","dependency_job_id":null,"html_url":"https://github.com/avala-ai/agent-code","commit_stats":null,"previous_names":["avala-ai/rust-code","avala-ai/rs-code"],"tags_count":50,"template":false,"template_full_name":null,"purl":"pkg:github/avala-ai/agent-code","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/avala-ai%2Fagent-code","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/avala-ai%2Fagent-code/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/avala-ai%2Fagent-code/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/avala-ai%2Fagent-code/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/avala-ai","download_url":"https://codeload.github.com/avala-ai/agent-code/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/avala-ai%2Fagent-code/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32602736,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-03T22:12:39.696Z","status":"online","status_checked_at":"2026-05-04T02:00:06.625Z","response_time":58,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["coding-agent"],"created_at":"2026-04-02T20:54:25.961Z","updated_at":"2026-05-04T10:05:27.719Z","avatar_url":"https://github.com/avala-ai.png","language":"Rust","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003cimg src=\"https://siuhyr0peaacfwst.public.blob.vercel-storage.com/avala-marketing-site/news/avala-bot-no-bg.png\" alt=\"Agent Code\" width=\"200\"\u003e\n\u003c/p\u003e\n\n\u003ch1 align=\"center\"\u003eAgent Code\u003c/h1\u003e\n\n\u003cp align=\"center\"\u003e\n  AI coding agent for the terminal. Built in Rust.\u003cbr\u003e\n  \u003ca href=\"https://github.com/avala-ai\"\u003eAvala AI\u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://crates.io/crates/agent-code\"\u003e\u003cimg src=\"https://img.shields.io/crates/v/agent-code.svg\" alt=\"crates.io\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/avala-ai/agent-code/actions\"\u003e\u003cimg src=\"https://github.com/avala-ai/agent-code/actions/workflows/ci.yml/badge.svg\" alt=\"CI\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://codecov.io/gh/avala-ai/agent-code\"\u003e\u003cimg src=\"https://codecov.io/gh/avala-ai/agent-code/branch/main/graph/badge.svg\" alt=\"Coverage\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/avala-ai/agent-code/blob/main/LICENSE\"\u003e\u003cimg src=\"https://img.shields.io/badge/license-MIT-blue.svg\" alt=\"MIT License\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n---\n\n## Install\n\n```bash\ncurl -fsSL https://raw.githubusercontent.com/avala-ai/agent-code/main/install.sh | bash\n```\n\nOr: `cargo install agent-code` / `brew install avala-ai/tap/agent-code`\n\n## Quickstart\n\n```bash\nagent                         # interactive mode (runs setup wizard on first launch)\nagent --prompt \"fix the tests\" # one-shot mode\nagent --model gpt-5.4         # use a specific model\n```\n\nThe agent reads your codebase, runs commands, edits files, and handles multi-step tasks. Type `?` for keyboard shortcuts.\n\n## LLM Providers\n\nWorks with any LLM. Set one env var and go:\n\n| Provider | Env Variable | Default Model |\n|----------|-------------|---------------|\n| OpenAI | `OPENAI_API_KEY` | gpt-5.4 |\n| Anthropic | `ANTHROPIC_API_KEY` | claude-sonnet-4 |\n| xAI | `XAI_API_KEY` | grok-3 |\n| Google | `GOOGLE_API_KEY` | gemini-2.5-flash |\n| DeepSeek | `DEEPSEEK_API_KEY` | deepseek-chat |\n| Groq | `GROQ_API_KEY` | llama-3.3-70b |\n| Mistral | `MISTRAL_API_KEY` | mistral-large |\n| Together | `TOGETHER_API_KEY` | meta-llama-3.1-70b |\n| Zhipu (z.ai) | `ZHIPU_API_KEY` | glm-4.7 |\n| Ollama | (none) | qwen3:latest |\n| AWS Bedrock | `AGENT_CODE_USE_BEDROCK` | claude-sonnet-4 |\n| Google Vertex | `AGENT_CODE_USE_VERTEX` | claude-sonnet-4 |\n| OpenRouter | `OPENROUTER_API_KEY` | anthropic/claude-sonnet-4 |\n| Cohere | `COHERE_API_KEY` | command-r-plus |\n| Perplexity | `PERPLEXITY_API_KEY` | sonar-pro |\n\nPlus any OpenAI-compatible endpoint: `agent --api-base-url http://localhost:8080/v1`\n\nAlready signed in with OpenAI Codex? Run `codex login`, then start agent-code with\n`agent --auth-mode codex_chatgpt --model gpt-5.4` to reuse that ChatGPT session.\n\n## Input Modes\n\n| Prefix | Action |\n|--------|--------|\n| (none) | Chat with the agent |\n| `!` | Run shell command directly |\n| `/` | Slash commands (tab-complete) |\n| `@` | Attach file to prompt |\n| `\u0026` | Run prompt in background |\n| `?` | Toggle shortcuts panel |\n| `\\` + Enter | Multi-line input |\n\n## Built-in Tools\n\nFile ops, search, shell, git worktrees, web access, LSP diagnostics, MCP resources, notebooks, background-task monitoring, scheduled routines, remote triggers, briefs, scoped config updates, MCP auth, tasks, and more. Tools execute during LLM streaming for faster turns. [Full list -\u003e](docs/reference/tools.mdx)\n\n## Bundled Skills\n\n| Skill | Purpose |\n|-------|---------|\n| `/commit` | Create well-crafted git commits |\n| `/review` | Review diff for bugs and security issues |\n| `/test` | Run tests and fix failures |\n| `/explain` | Explain how code works |\n| `/debug` | Debug errors with root cause analysis |\n| `/pr` | Create pull requests |\n| `/refactor` | Refactor code for quality |\n| `/init` | Initialize project configuration |\n| `/security-review` | OWASP-oriented vulnerability scan |\n| `/pentest` | White-box penetration test with proof-of-concept gating |\n| `/advisor` | Architecture and dependency health analysis |\n| `/bughunter` | Systematic bug search |\n| `/plan` | Structured implementation planning |\n| `/changelog` | Generate changelog entries from commit history |\n| `/release` | Cut a versioned release |\n| `/benchmark` | Run and compare benchmarks |\n| `/coverage` | Measure and report test coverage |\n| `/migrate` | Apply codebase-wide migrations |\n| `/docs` | Generate or update documentation |\n| `/remember` | Save a specific insight to user memory (two-step write discipline) |\n| `/stuck` | Step back and try a different angle when the agent is looping |\n| `/simplify` | Review-then-simplify pass: flag dead weight in the current diff |\n| `/batch` | Apply the same change across multiple git worktrees |\n| `/skillify` | Extract the successful workflow from this session into a reusable skill |\n\nAdd custom skills as markdown files in `.agent/skills/` or `~/.config/agent-code/skills/`.\n\n## Configuration\n\n```toml\n# ~/.config/agent-code/config.toml\n\n[api]\nmodel = \"gpt-5.4\"\n\n[permissions]\ndefault_mode = \"ask\"   # ask | allow | deny | accept_edits | plan\n\n[features]\ntoken_budget = true\nextract_memories = true\nauto_theme = true\n\n[security]\nmcp_server_allowlist = [\"github\", \"filesystem\"]\ndisable_bypass_permissions = true\n```\n\n## Architecture\n\n```\ncrates/\n  lib/   agent-code-lib    Engine: providers, tools, query loop, memory\n  cli/   agent-code        Binary: REPL, TUI, commands, setup wizard\n  eval/  agent-code-eval   Evaluation harness for benchmarking the engine\n\npackages/\n  agent_code_client        Dart client library for talking to the engine\n\nclient/                    Cross-platform Flutter desktop/web GUI (see client/README.md)\n```\n\nThe engine is a reusable library. The CLI binary is a thin wrapper. The Flutter client in `client/` is a separate front-end that talks to the engine via the `agent_code_client` package.\n\n## Slash Commands\n\nSession management, context control, git operations, agent coordination, configuration, diagnostics, and more. [Full list -\u003e](docs/reference/commands.mdx)\n\nHighlights: `/theme`, `/output-style`, `/plugin`, `/tools`, `/team-remember`, `/profile`, `/tokens`, `/thinkback`, `/pr-comments`, `/autofix-pr`, `/perf-issue`, `/release-notes`, `/summary`, `/update`, `/uninstall`, `/doctor`, `/model`, `/cost`, `/usage`, `/scroll`, `/rewind`, `/fork`, `/rename`, `/add-dir`, `/btw`\n\n## Security\n\nProtected directories (`.git/`, `.husky/`, `node_modules/`) are blocked from writes regardless of permission settings. Destructive shell commands trigger warnings. [Learn more -\u003e](SECURITY.md)\n\n## Platforms\n\n| Platform | Architecture | Install |\n|----------|-------------|---------|\n| Linux | x86_64, aarch64 | curl, cargo, homebrew, prebuilt binary |\n| macOS | x86_64, Apple Silicon | curl, cargo, homebrew, prebuilt binary |\n| Windows | x86_64 | cargo, prebuilt binary (.zip) |\n| Docker | any | `docker run ghcr.io/avala-ai/agent-code` |\n\n## Contributing\n\n```bash\ngit clone https://github.com/avala-ai/agent-code.git\ncd agent-code\ncargo check --all-targets\ncargo test --all-targets\ncargo clippy --all-targets -- -D warnings\ncargo fmt --all -- --check\n```\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines, [RELEASING.md](RELEASING.md) for release steps, and [ROADMAP.md](ROADMAP.md) for planned improvements.\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Favala-ai%2Fagent-code","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Favala-ai%2Fagent-code","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Favala-ai%2Fagent-code/lists"}