Skip to content

Latest commit

 

History

85 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Respondami

v0.1.0 — privacy-first coding agent. One binary, no telemetry, skills-driven.

Built with Ratatui and Crossterm.

Respondami demo

⚠️ No Permission System

Respondami has no permission gates — tool calls execute immediately without asking for approval. The agent has full autonomy to read, write, edit files, and run shell commands. Run it inside a sandbox (container, VM, or bubblewrap) to protect your system.

Installation

From Source

git clone https://github.com/sorcerersr/respondami.git
cd respondami
cargo build --release

The binary is at target/release/respondami.

Prerequisites

  • Rust (latest stable)
  • CMake (required for aws-lc-sys)
  • A running LLM backend (e.g. llama.cpp server)

Quick Start

  1. Start your LLM server (e.g. llama-server -m model.gguf)
  2. Run Respondami: ./target/release/respondami
  3. Configure: On first run, Respondami creates ~/.config/respondami/config.json with defaults. Edit it to point to your LLM server.
  4. Send a message: Type in the input area and press Enter.

For a detailed walkthrough, see docs/quick-start.md.

Features

  • Session management — persist conversations as JSONL, resume across sessions
  • Automatic compaction — LLM summarization keeps conversations within the context window
  • Skills — self-contained capability packages (open standard, agentskills.io)
  • Hooks — shell scripts at lifecycle points to inject context, block actions, or run side effects
  • RTK integration — automatic command rewriting for safer shell execution
  • Project instructionsAGENTS.md loaded into the system prompt on every turn

Documentation

Document Description
Quick Start Getting started, key bindings, status bar
Configuration All config options, directory layout
Skills Using and creating skills
Hooks Lifecycle hooks, events, examples
Logging Log file, debug levels, SSE debug capture
Security Threat model, sandboxing recommendations
Troubleshooting Common issues and fixes

Development

cargo build --release            # build
cargo run                        # run the TUI
cargo clippy --all-targets --all-features   # must be clean (0 errors, 0 warnings)
cargo test                                    # all tests must pass

License

Copyright (c) Stefan "Sorcerer" Rabmund

This project is licensed under the MIT license (LICENSE or http://opensource.org/licenses/MIT)

About

Privacy-first coding agent. One binary, no telemetry, skills-driven

Resources

Security policy

Stars

0 stars

Watchers

0 watching

Forks

Releases

Used by

Contributors

Languages