Skip to main content
Glama

kagero

license

Kagero — one Agent interface over coding-agent CLIs, exposed as an MCP server and a CLI. Ten backends, seven honest tools, zero pretending: whatever a backend cannot do comes back as an explicit [unsupported_capability] error, never as a guess.

Backends

backend

transport

binary

pi-sdk

in-process SDK (@earendil-works/pi-coding-agent, optional peer dep)

pi-rpc

subprocess, pi --mode rpc

pi

claude

subprocess, claude -p --output-format stream-json

claude

claude-stream

long-lived subprocess, live --input-format stream-json protocol (steer/follow_up/interrupt)

claude

codex

subprocess, codex exec --json

codex

dsh

subprocess, dsh --profile headless (dsh-headless-bridge)

dsh

grok

subprocess, grok ACP + streaming print

grok

kimi

subprocess, kimi acp / print

kimi

mcode

subprocess, mcode acp / mcode exec

mcode

qwen

subprocess, qwen --acp / stream / print

qwen

Select with KAGERO_BACKEND or kagero mcp --backend=<name>; kagero backends lists what is registered.

Related MCP server: all-agents-mcp

Install

npm install kagero-mcp
# or run without installing
npx kagero-mcp

The pi-sdk backend needs its optional peer dependency:

npm install @earendil-works/pi-coding-agent

Usage

CLI

kagero prompt "List the files in the current directory"   # one-shot
KAGERO_BACKEND=mcode kagero prompt "…"                    # pick a backend
kagero backends                                           # registered backends
kagero models                                             # active backend models
kagero sessions                                           # persistent sessions
kagero mcp --backend=mcode                                # MCP server over stdio

MCP tools

run (fresh prompt, or continue a session via session_id; blocking or run_in_background), send_message (steer / follow_up / abort), task_list, task_output, task_stop (the background-run registry), history, info.

A background run returns {task_id, status: "running"} immediately; when it finishes a task-completed logging notification announces the outcome and task_output returns the final result.

History

history returns a compact normalized view, paged from the newest end (page / page_size, entry indexes are global across pages) with a full-log pointer. Readers for pi, qwen, grok, kimi, mcode (MiniMax Code), claude, codex and dsh parse each CLI's on-disk session logs, capture thinking blocks and merge tool results into their calls.

Session compression (optional)

Set KAGERO_COMPRESS_BACKEND (and optionally KAGERO_COMPRESS_MODEL) to enable run reports and the compressed live stream: agent event streams are compressed by a cheap second agent into anchored, machine-validated digests — per-move blocks with distilled reasoning, a rolling checkpoint and a status verdict. history prepends the digest header when one exists and task_output (include_blocks) returns the compressed blocks. Compressed state persists across restarts in a crash-safe journal (~/.kagero/watch/).

Architecture

Agent interface (@kagero/core)
  ├─ CliSpecAgent (@kagero/cli-backend) — spec-driven print/ACP transports,
  │    history readers, stream-json parsers
  ├─ PiSdkAgent / PiRpcAgent (@kagero/pi-backend)
  ├─ ClaudeStreamAgent (@kagero/cli-backend) — live stream-json protocol
  └─ createKageroMcpServer (@kagero/mcp) — MCP factory over any registry

See docs/ARCHITECTURE.md for the full contract.

Security & behavior

  • Strict schemas. Every tool input is enforced with z.object(...).strict(); unknown fields are rejected before they reach a backend.

  • Honest statuses. Runs end completed, aborted, timed-out or with the CLI's own error — a killed run is never success.

  • Fail-closed permissions. Live transports answer reverse permission requests with an explicit deny; nothing is auto-approved headlessly.

  • No resource leaks. Process groups are killed through a SIGTERM → grace → SIGKILL ladder; ACP clients outlive single runs and are disposed on shutdown.

License

MIT

Related MCP Connectors

Related MCP Servers

  • A
    license
    A
    quality
    F
    maintenance
    Provides unified access to multiple CLI AI agents (Codex, Gemini, Claude, and OpenCode) through a single MCP interface with real-time task monitoring, enabling specialized code analysis, UI design, implementation, and prototyping workflows.
    11
    21
    MIT
  • A
    license
    B
    quality
    F
    maintenance
    Enables orchestrating multiple AI CLI agents (Claude Code, Codex, Gemini CLI, Copilot CLI) through a unified MCP interface for task delegation, cross-agent comparison, and specialized tools like code review and debugging.
    14
    4 npm
    14
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Unified CLI multiplexer for AI coding agents, enabling orchestration of multiple coding CLI tools through a single interface with session persistence, cost tracking, and MCP tool support.
    13 npm
    19
    MIT