Skip to content

Supported Agents

Codeg drives eleven coding agents, and once one is running they all feel the same — same composer, same diffs, same git and terminal — because Codeg talks to each over the Agent Client Protocol (ACP). What differs is underneath: who builds the agent, what runtime it needs on your machine, and where it keeps its own history. This page is the map.

Enabling an agent, its preflight health check, and starting a session are covered in Working with Agents; signing in and choosing a model are in Authentication & Models. Here we stick to the roster itself.

The roster

Codeg installs, pins, and updates every one of these for you — you never fetch one by hand. What you do need on your machine is the runtime each agent runs on:

AgentWhat it isRuns on
Claude CodeAnthropic's Claude coding agentNode.js
CodexOpenAI's coding-assistant CLINode.js
GeminiGoogle's official Gemini CLINode.js
OpenClawA personal AI assistant you self-hostNode.js
OpenCodeAn open-source coding agentBundled binary
ClineAn autonomous coding-agent CLINode.js
HermesNous Research's self-improving agentPython (uv)
CodeBuddyTencent Cloud's AI coding assistantNode.js
Kimi CodeMoonshot AI's CLI coding assistantNode.js
PiA self-extensible coding agentNode.js
GrokxAI's coding agent and CLINode.js

Three delivery routes sit behind that last column:

  • Node.js (npm). Nine of the eleven ship as npm packages that Codeg runs with npx, so they need Node.js installed. Codeg pins a known-good version of each and upgrades it for you.
  • Bundled binary. OpenCode is a native binary Codeg downloads for your exact platform — nothing else to install.
  • Python (uv). Hermes runs through uv, the Python tool runner; Codeg launches it with a pinned Python, so you don't manage the environment.

The order above is the default Agent List order in Settings → Agents. It's a preference, not a ranking — drag agents to reorder them, and the first enabled one becomes Codeg's fallback when nothing else has picked the agent for a conversation. → Working with Agents

Where each agent keeps its sessions

Every agent stores its own conversation history in its own place and format, long before Codeg is in the picture. That's exactly what Conversation Aggregation reads when it imports your past work: Codeg looks in each agent's native store for sessions you ran in the folder you're importing, and lists what it finds.

Here's where "each agent's native store" actually lives:

AgentDefault locationFormatRelocate with
Claude Code~/.claude/projects/JSONLCLAUDE_CONFIG_DIR
Codex~/.codex/sessions/JSONLCODEX_HOME
Gemini~/.gemini/JSON filesGEMINI_CLI_HOME
OpenClaw~/.openclaw/agents/JSONL
OpenCode~/.local/share/opencode/opencode.dbSQLiteXDG_DATA_HOME
Cline~/.cline/data/JSON filesCLINE_DIR
Hermes~/.hermes/state.dbSQLiteHERMES_HOME
CodeBuddy~/.codebuddy/projects/JSONLCODEBUDDY_CONFIG_DIR
Kimi Code~/.kimi-code/sessions/JSONLKIMI_CODE_HOME
Pi~/.pi/agent/sessions/JSONLPI_CODING_AGENT_SESSION_DIR
Grok~/.grok/sessions/JSONLGROK_HOME

Most agents write a JSONL transcript — a plain-text log, one event per line — while OpenCode and Hermes keep everything in a single SQLite database and Gemini and Cline use their own JSON files. Codeg reads each format natively; you never convert anything.

Moved a store? Codeg follows the same variable.

Point an agent at a non-default location with one of the environment variables above and Codeg honors it too — so a relocated history still imports — as long as Codeg sees that variable in its own environment. OpenClaw is the exception: its store isn't relocatable.

How agents differ

The surface is identical, but a few things vary by agent — worth knowing so nothing catches you off guard:

  • Models and modes come from the agent, not Codeg. The model dropdown and the mode dropdown (plan-first, accept-edits, and the like) list whatever the connected agent reports over ACP. Two agents will offer different models and different modes — that's the agent talking, not a Codeg setting. → Authentication & Models
  • Sign-in differs too. Some agents log in with their own subscription or OAuth, others take a provider API key or a custom endpoint. Each agent's detail pane shows only the options that apply to it. → Authentication & Models
  • OpenClaw opts out of MCP. It's the one agent that doesn't accept Model Context Protocol servers, so an MCP server you've added won't reach an OpenClaw session — Codeg forwards none to it. Most other agents receive your MCP servers normally. → MCP Servers

Next steps

Released under the Apache-2.0 License.