Skip to content

pierreprudh/KLIDE

Repository files navigation

Klide

Every agent visible. Every change reviewable.

A local-first coding workspace for running local models and subscription coding agents side by side.


Version Platform License


Get started  ·  Features  ·  Architecture  ·  Contributing


Klide running Ollama, OpenRouter, MLX, and OpenCode in one workspace

One workspace for every coding agent

Klide runs Ollama, MLX, Claude Code, Codex, OpenCode, and Oh My Pi (OMP) without hiding their native capabilities. You can inspect tool calls, follow terminal output, compare model cost and latency, and review changes from one workspace.

Klide keeps three questions in view:

  • What is running? Mission Control tracks Klide runs and delegate command-line interface (CLI) sessions
  • What needs attention? Waiting, blocked, failed, and reviewable work rises to the top
  • What changed? Each run keeps its files, branch, transcript, validation state, cost, and memory evidence

Why Klide

Coding agents work well in terminals, but their sessions, diffs, and evidence spread across separate tools. Klide keeps the real terminal experience and adds a shared operations layer around it.

Run real agents Use Claude Code, Codex, OpenCode, OMP, or a custom CLI inside persistent pseudoterminal (PTY) sessions
Keep work visible See working, waiting, blocked, and completed runs across the workspace
Review before trust Approve commands, inspect proposed edits, comment on diffs, and check validation evidence
Choose where inference runs Start with Ollama or MLX, then opt into hosted providers or subscription CLIs
Resume with context Reopen transcripts, hand work to another agent, and save reviewed project memory

How work moves through Klide

  1. Start a Klide run or open a delegate CLI
  2. Follow its status, tool calls, terminal output, and changed files
  3. Review edits and commands before they cross the workspace trust boundary
  4. Validate the result, send feedback, resume later, or hand the work to another agent

Klide has three capability modes:

Mode Agent access
Chat Answers without workspace tools
Plan Reads the workspace and proposes an approach
Goal Uses tools with diff review and permission-gated commands

Features

Area Included
Agent operations Mission Control, shared run lifecycle, attention queue, transcripts, session resume, cross-agent handoff, sub-agent visibility
Review and evidence Diff comments sent to agents, command approval, checkpoints, validation status, files touched, tokens, cost, and stop reasons
Parallel work Git worktrees, worktree setup recipes, branch comparison, and merge controls
Editor and shell Monaco editor, file explorer, tabs, search, command palette, Git review, commit graph, and persistent PTY terminals
Models Ollama, MLX, Anthropic, OpenAI, Mistral, xAI, OpenRouter, and OpenAI-compatible endpoints
Project context AGENTS.md, CLAUDE.md, file mentions, skills, dynamic tools, and reviewed project memory
Local security Workspace-rooted file access, operating-system keychain storage, project command allowlists, and network permissions

Get started

Klide currently targets macOS. Apple Silicon is the primary development platform.

Prerequisites

Build from source

Clone the repository and start the Tauri development build:

git clone https://github.com/pierreprudh/KLIDE.git
cd KLIDE
npm install
npm run tauri dev

The first Rust build takes about three to five minutes. Later builds reuse the compiled dependencies.

Once Klide opens:

  1. Open a workspace folder
  2. Open the AI panel and select a provider
  3. Press Tab to switch between Chat, Plan, and Goal
  4. Open Mission Control to follow active and completed work

⌘P jumps to a file, ⌘⇧P opens the command palette, and ⌘/ shows the full shortcut cheatsheet.

Use the Klide model

pierreprudh/klide-8b is a Low-Rank Adaptation (LoRA) fine-tune of LFM2.5-8B-A1B. It is trained for Klide's tool and edit contract.

ollama pull pierreprudh/klide-8b

The model appears in Klide's Ollama picker after the download finishes.

Trust and architecture

Klide separates the interface from the durable execution layer:

Layer Responsibility
React and TypeScript Editor, panels, review surfaces, layouts, and run projections
Tauri and Rust Agent harness, provider streaming, tools, permissions, PTYs, Git, keychain, and filesystem access
JSON Lines (JSONL) transcripts Append-only run events used by Mission Control, validation, memory, and replay

The Rust harness checks capabilities when it advertises tools and again before execution. Writes pause for diff review. Commands and network access pause for permission.

Read the Harness contract for the trust model and Harness schema for the tool interface.

Project status

Klide is at version 0.5 and remains under active development. Source builds are available now; signed application bundles are not yet published.

Current priorities:

  • Make worktree-per-run isolation the default parallel-agent flow
  • Deepen the review queue and agent feedback loop
  • Publish signed macOS builds, then validate Windows and Linux

See the changelog for shipped milestones.

Development

Run the relevant checks before submitting a change:

npm test
npm run build
cargo test --manifest-path src-tauri/Cargo.toml

The frontend lives in src/. The Rust backend lives in src-tauri/.

Contributing

Issues and pull requests are welcome. Keep changes focused, preserve the workspace trust boundary, and include validation for changed behavior.

Acknowledgments

Klide is built with Tauri, Monaco, and xterm.js. Its product influences include Sinew, Ara, Cursor, Cline, Linear, and the open coding-agent ecosystem.

License

Klide is available under the MIT License.

Releases

No releases published

Packages

 
 
 

Contributors