Dev & Engineering terminal-codinggo-climcpmulti-providersandbox-policystream-jsonlocal-sessions

Zero

A local terminal coding agent with your choice of model and permission policy.

FollowAgents review · FARS-2.0
Not yet reviewed
See the full review method →

What does this agent do, and when should you use it?

Zero is an AI coding agent for the local terminal, with both an interactive TUI and the scriptable `zero exec` command. It can inspect repositories, edit files, run commands, and use local browser and terminal helpers; its sessions are stored on disk and can be searched, resumed, or forked. Users can configure models from 25+ providers, including OpenAI, Anthropic, Gemini, Ollama, LM Studio, and compatible endpoints. Its headless mode supports text, JSON, and stream-JSON I/O, isolated worktrees, and spec-first runs for scripting or CI. File writes, shell commands, network access, and writes outside the workspace are governed by permission and sandbox policy.

Run zero for the terminal TUI or zero exec "..." for a one-shot coding task. The agent can read the local workspace, modify workspace files, run shell commands through exec_command, and retrieve public URLs through web_fetch; its permission and sandbox policy governs those side effects. zero exec accepts text prompts and can process JSONL turns with --input-format stream-json --output-format stream-json; --worktree runs in an isolated Git worktree, while --resume and --fork continue or branch local sessions. It also manages MCP servers and tools through zero mcp, and zero serve --mcp exposes Zero tools over MCP stdio.

  1. A developer using OpenAI, Anthropic, or Gemini APIs who wants an agent in their terminal to inspect a repository and fix a failing test.
  2. A local-model user running Ollama or LM Studio who needs to configure local inference without moving to a vendor-specific coding client.
  3. An engineer maintaining CI or automation scripts who needs to send tasks through `zero exec` and consume JSON or stream-JSON output.
  4. A developer testing a migration or refactor who wants to run an agent task in an isolated Git worktree with `zero exec --worktree`.
  5. A contributor working across codebases who needs to grant an additional, limited write directory to the current session with `--add-dir`.

What are this agent's strengths and limitations?

Pros
  • It combines an interactive TUI with a headless `zero exec` interface that supports text, JSON, and stream-JSON I/O for scripting and CI.
  • It documents a broad provider path: OpenAI, Anthropic, Gemini, Ollama, LM Studio, and OpenAI- or Anthropic-compatible endpoints are among the listed options.
  • Its permission model specifically covers file writes, shell commands, network access, and writes outside the workspace, with scoped extra write roots through `--add-dir`.
  • Local sessions are searchable, resumable, forkable, and rewindable; the README states that Zero does not upload them as telemetry.
Limitations
  • Source builds require Go 1.26.5+, and native Linux sandboxing requires building and placing the separate `zero-linux-sandbox` helper beside the main binary.
  • Remote API providers require users to configure the relevant API key; model availability and cost depend on the selected provider.
  • The listed official npm builds support Windows x64; Windows on ARM runs the x64 build under emulation.
  • The release installers and npm wrapper depend on published GitHub Release assets; before the first public release, the documented path is building from source.

How do you install or deploy this agent?

Install with npm:
npm install -g @gitlawb/zero
zero

Building from source requires Go 1.26.5+:
git clone https://github.com/Gitlawb/zero.git
cd zero
go run ./cmd/zero

For an API provider, set the matching key before zero setup or enter it in the setup wizard. For example:
export OPENAI_API_KEY=sk-...
zero setup
For local models, start Ollama or LM Studio, then run zero setup or zero providers detect.

How do you use this agent?

Start the interactive interface:
zero

Run a one-shot task:
zero exec "fix the failing test in ./pkg"

Select a model for a task:
zero exec --model claude-sonnet-4.5 "refactor the config loader"

Use stream-JSON I/O:
zero exec --input-format stream-json --output-format stream-json < turns.jsonl

Use zero doctor to check setup, keys, and connectivity; use zero providers list and zero models list to inspect configuration.

FAQ

Is Zero limited to one model provider?
No. The documentation lists 25+ providers, including OpenAI, Anthropic, Gemini, Groq, OpenRouter, Ollama, and LM Studio, plus OpenAI- and Anthropic-compatible endpoints.
Does it get unrestricted filesystem and network access by default?
No. Workspace reads are allowed by default and writes are limited to the workspace. Shell commands, network access, destructive commands, elevated actions, and out-of-workspace writes are permission-gated.
Can it be used in automation or CI?
Yes. `zero exec` supports scriptable execution, isolated worktrees, spec-first runs, meaningful exit codes, and JSON or stream-JSON input and output.
Where do sessions and context live?
The README states that sessions are stored on disk and can be searched, resumed, and forked; Zero does not upload them as telemetry.

Related agents