Claude Code 2.0
JuryiBay/claude-code-2.0
Agent de codificação local com LLM via Ollama, sem APIs de nuvem
Ver no GitHubAgent de codificação em terminal totalmente local, alimentado por um modelo LLM via Ollama. Lê, busca, edita e executa código em sua máquina sem dependências externas, APIs de nuvem ou chaves — seu código nunca sai do computador.
Instalação
npx convez-ai JuryiBay/claude-code-2.01 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Desenvolver e refatorar código localmente com assistência IA
- Executar tarefas de codificação em ambientes sem conectividade
- Manter código privado sem enviar para serviços de nuvem
- Validação e edição de código com aprovação manual de mudanças
Veredito

Solução robusta para desenvolvimento local sem dependência de APIs em nuvem. Ideal para quem prioriza privacidade e controle total, mas exige setup local (Ollama + modelo) e aprovação manual de operações — não é plug-and-play.
README
A tradução para o português deste README ainda está na fila.
CLAUDE CODE 2.0
A fully local, original terminal AI coding agent. It reads, searches, edits, and runs your code on your machine — and the "brain" is a local LLM served by Ollama. There are no cloud APIs, no API keys, and zero runtime dependencies. Your code never leaves your computer.
CLAUDE CODE 2.0 · local terminal coding agent
────────────────────────────────────────────────────
model qwen2.5-coder
engine http://127.0.0.1:11434 (local Ollama)
cwd C:\Users\you\my-project
help /help /clear /auto /exit
────────────────────────────────────────────────────
› add input validation to the signup handler
● I'll look at the handler first.
▸ grep signup
▸ read_file src/routes/signup.ts
● The handler trusts the request body directly. I'll add validation…
▸ edit_file src/routes/signup.ts
⚠ edit_file: Edit src/routes/signup.ts
Approve? [y/N] y
● Done. Added length/format checks and a 400 response on bad input.
How it works
your prompt ──► agent loop ──► local Ollama model (qwen2.5-coder, …)
▲ │
│ wants to use a tool?
tool result ◄── run tool ◄───┘
(read / write / edit / list / grep / glob / run_command)
The agent runs a tool-calling loop entirely against your local model. When the model asks to write a file or run a command, you approve it (unless auto-approve is on).
Requirements
- Node.js 18.18+ (uses the built-in
fetch). - Ollama running locally.
- A tool-capable local model:
qwen2.5-coder,llama3.1,mistral-nemo,qwen3, …
Setup
Windows
- Install Node.js (LTS) from https://nodejs.org.
- Install Ollama for Windows from https://ollama.com/download. It runs a local
server at
http://127.0.0.1:11434automatically. - Pull a coding model (on an RTX 5080, the 14B variant is a great fit):
ollama pull qwen2.5-coder:14b - In this project folder:
Editnpm install copy .env.example .env.envand setCC2_MODEL=qwen2.5-coder:14b. - Run it from inside the project you want to work on:
npm start
macOS / Linux
brew install ollama # or see ollama.com
ollama serve # start the local server (if not already running)
ollama pull qwen2.5-coder
npm install
cp .env.example .env
npm start
Usage
# Interactive REPL (run it from the directory you want the agent to work in)
npm start
# One-shot task
npm start -- "explain what src/index.ts does"
# Auto-approve writes and commands (use with care)
npm start -- --auto "run the test suite and fix any failures"
# Read-only: the agent can explore but never writes or runs commands
npm start -- --readonly "review this project for bugs"
REPL commands
| Command | Action |
|---|---|
/help | Show help |
/clear | Reset the conversation context |
/auto | Toggle auto-approve for writes and commands |
/exit | Quit (/quit works too) |
Tools the agent can use
| Tool | Read-only | Purpose |
|---|---|---|
read_file | yes | Read a file with line numbers (supports offset/limit) |
list_dir | yes | List a directory's entries |
glob | yes | Find files by glob pattern (**, *) |
grep | yes | Search file contents by regular expression |
edit_file | no | Replace a unique string in a file (asks first) |
write_file | no | Create/overwrite a file (asks first) |
run_command | no | Run a shell command — cmd.exe/sh (asks first) |
Configuration (.env)
| Variable | Default | Meaning |
|---|---|---|
CC2_OLLAMA_URL | http://127.0.0.1:11434 | Local Ollama server URL |
CC2_MODEL | qwen2.5-coder | Local model (must support tool calling) |
CC2_TEMPERATURE | 0.2 | Sampling temperature |
CC2_NUM_CTX | (model default) | Context window size in tokens |
CC2_TIMEOUT_MS | 300000 | Abort if the model sends no data for this long (prevents hangs) |
Windows note:
run_commandoutput is decoded as UTF-8. On a non-UTF-8 Windows console code page (e.g. cp866), non-ASCII command output may appear garbled. If you need it, prefix the command withchcp 65001>nul & …to switch the console to UTF-8 first.
Safety model
- The agent is sandboxed to the working directory — any path that escapes it is blocked.
- Writes, edits, and shell commands require your approval unless
--autois set. --readonlylets the agent explore without changing anything.
Project layout
src/
├── index.ts # CLI entry: config, preflight, REPL / one-shot
├── config.ts # .env loader + configuration
├── api/ollama.ts # local Ollama chat client (streaming + tools)
├── agent/
│ ├── loop.ts # the tool-calling agent loop
│ └── systemPrompt.ts # the agent's instructions
├── tools/ # read / write / edit / list / grep / glob / run_command
├── permissions/guard.ts# approval policy (ask / auto / readonly)
├── ui/ # ansi colors, prompt, rendering, spinner
└── util/ # path sandbox, recursive walk + glob, arg validation
Scripts
npm start # run the agent
npm run dev # run with auto-restart on file changes
npm test # run the unit tests
npm run typecheck# type-check the project
License
MIT. Original code — no third-party agent framework, no cloud services.