Openharness

io.github.philo-kimPublished by GitHub account philo-kimv0.1.1Updated Oct 24, 2026

Lets AI coding agents discover and reference each other's recent sessions.

VerifiedSTDIODesktop onlyKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

A local MCP server that lets AI coding agents find each other's recent session files so one agent can reference another's work.

What you can do
List recent session paths and metadata for all supported agents, filtered by project path, with format and update time, and whether the match came from a directory name, a workspace field or a path hash. Look up the most recent session path for one named agent, returning null when none is found. Supported agents are Claude Code, Codex CLI and Gemini CLI. It only returns paths and metadata; the calling agent reads the session files itself.
When to use it
Useful when you run several coding agents on the same project and want one to review or build on what another recently did, for example asking Codex to review Claude Code's latest session. Not needed if you use a single agent or do not want agents reading each other's local session files.
Requirements
Runs as a local process installed from the npm package, so Node.js and npm are needed. Each agent must be able to read local files directly. Setup registers the server in each agent's config, either through the init command or by adding a manual MCP entry. No accounts, API keys or environment variables are declared.
Before you install
It exposes paths to local session files, which may contain sensitive conversation content; the server itself does not read, transform or store that content, but the calling agent will read the files directly. Installing globally and running the init command modifies each agent's MCP configuration files.

Installation

In SourceWeft

  1. Open Openharness in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

OpenHarness

AI 코딩 에이전트의 최근 세션 파일을 찾아 서로 참조하게 해주는 로컬 MCP 서버.

전용 하네스 없이 하네스처럼 동작한다. 기존 도구 환경을 그대로 유지하면서, 에이전트 간 세션을 연결하는 디스커버리 레이어.

Supported Agents (MVP)

AgentSession PathFormat
Claude Code~/.claude/projects/JSONL
Codex CLI~/.codex/sessions/JSONL
Gemini CLI~/.gemini/tmp/<hash>/chats/JSON

Prerequisites

  • Each agent must be able to read local files directly.
  • OpenHarness only provides paths and metadata — it does not transform, relay, or store session content.

Install

bash
npm install -g @freebird-ai/openharnessopenharness init

This registers OpenHarness as an MCP server in each agent's config.

MCP Tools

get_agent_sessions

Returns recent session paths for all agents, filtered by project.

Input:

json
{ "project": "/Users/me/my-app" }

Output:

json
[  {    "agent": "claude-code",    "path": "/Users/me/.claude/projects/-Users-me-my-app/session.jsonl",    "format": "jsonl",    "updatedAt": "2026-03-17T14:32:00Z",    "matchedProject": "/Users/me/my-app",    "matchedBy": "directory-name"  }]

get_agent_session

Returns the recent session path for a specific agent.

Input:

json
{ "agent": "claude-code", "project": "/Users/me/my-app" }

Output:

json
{  "agent": "claude-code",  "path": "/Users/me/.claude/projects/-Users-me-my-app/session.jsonl",  "format": "jsonl",  "updatedAt": "2026-03-17T14:32:00Z",  "matchedProject": "/Users/me/my-app",  "matchedBy": "directory-name"}

Returns null if no session is found.

Project Matching

AgentStrategy
Claude CodeProject path escaped with - as directory name
Codex CLIWorkspace field inside session JSONL
Gemini CLIProject path hash matching tmp/<hash>/

How It Works

User → Codex: "Review what Claude Code worked on recently"
Codex → OpenHarness MCP: get_agent_session({ agent: "claude-code", project: "..." })Codex ← receives session path + metadataCodex → reads the JSONL file directly and performs review

No rules needed in agent instruction files. MCP tool descriptions are enough for agents to use naturally.

Manual MCP Configuration

If you prefer to configure manually instead of using init:

json
{  "mcpServers": {    "openharness": {      "command": "openharness",      "args": []    }  }}

Add this to your agent's MCP config file:

AgentConfig File
Claude Code~/.claude/mcp.json or project .mcp.json
Codex CLIproject .codex/
Gemini CLI~/.gemini/settings.json

License

MIT

Source: README.md at commit af0df79

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.