Agent Code
github.com
Spec sheet
- What it does
- Agent Code reads codebases, runs commands, edits files, and iterates on coding tasks.Read 12 Oct 2026 · github.com
- Purpose
- Agent Code is an open-source AI coding agent for the terminal that reads codebases, runs commands, edits files, and iterates on tasks.Read 12 Oct 2026 · avala-ai.github.io
- Platforms
- Prebuilt binaries are listed for macOS, Linux, and Windows.Read 12 Oct 2026 · github.com
- Free plan
- YesRead 22 Sep 2026 · github.com
- Integrations
- It supports MCP and ACP integrations and exposes a local HTTP API for clients, including the project’s Flutter GUI.Read 12 Oct 2026 · github.com
- Support
- The security policy asks vulnerability reports to be emailed to [email protected] and says reports are acknowledged within 48 hours.Read 12 Oct 2026 · github.com
- License
- Agent Code is released under the MIT license.Read 12 Oct 2026 · github.com
- Maker
- The GitHub organization identifies the maker as Avala AI and lists the United States of America as its location.Read 12 Oct 2026 · github.com
- Chat assistance
- YesRead 22 Sep 2026 · github.com
- Coding agent
- YesRead 22 Sep 2026 · github.com
- Data handling
- The security policy says session data is stored locally and conversation history leaves the machine only for LLM API calls.Read 12 Oct 2026 · github.com
- Features
- The project lists 30+ tools for files, shell, search, worktrees, web, LSP, MCP, and subagents, along with skills, plugins, and resumable sessions.Read 12 Oct 2026 · github.com
- Install options
- The README lists installation through Cargo, Homebrew, Docker, prebuilt binaries, or building from source.Read 12 Oct 2026 · github.com
- Model providers
- It supports providers including Anthropic, OpenAI, Azure OpenAI, xAI, Google, OpenRouter, and local OpenAI-compatible APIs.Read 12 Oct 2026 · github.com
- Open source
- The project is MIT licensed.Read 12 Oct 2026 · github.com
- Permissions
- Its security policy says tool calls pass through permission checks, with ask mode as the default and a read-only plan mode.Read 12 Oct 2026 · github.com
- Protected paths
- Write tools are blocked from modifying `.git/`, `.husky/`, and `node_modules/`.Read 12 Oct 2026 · github.com
- Requirements
- Installation requires an LLM API credential or subscription login; full tooling requires git and ripgrep, and Linux sandboxing optionally uses bwrap.Read 12 Oct 2026 · github.com
- Security controls
- The project documents permission modes, protected directories, destructive-command checks, system-path protections, and an optional OS sandbox.Read 12 Oct 2026 · github.com
- Security limits
- The threat model excludes the security of the LLM API endpoint and the user's local machine beyond what Agent Code touches.Read 12 Oct 2026 · github.com
- Security support
- The security policy asks users to report vulnerabilities by email, promises acknowledgment within 48 hours, and gives a fix-timeline response within five business days.Read 12 Oct 2026 · github.com
- Telemetry
- The README says telemetry is not sent unless the user opts in.Read 12 Oct 2026 · github.com
- Terminal access
- YesRead 22 Sep 2026 · github.com
- Tools
- The project lists more than 30 tools, including file operations, shell, search, web, LSP, MCP, and subagents.Read 12 Oct 2026 · github.com
- Usage modes
- It supports an interactive terminal UI, headless scripts and CI, an HTTP server, and the Agent Client Protocol for IDE integrations.Read 12 Oct 2026 · github.com
- Ways to run
- It supports an interactive terminal UI, headless scripts, a local HTTP API, and an ACP bridge for IDEs.Read 12 Oct 2026 · github.com
- Workflows
- It includes skills and plugins, project conventions, session resume, and a security scanning mode.Read 12 Oct 2026 · avala-ai.github.io
Plans and prices
Open source Free MIT-licensed software; requires a supported LLM credential Read 12 Oct 2026 · github.com
Where Specifiction places it
- AI Coding Assistants#35 of 1038.6