by i365dev
Free4Chat provides the temporary boundary. Participants bring the capabilities.
# Add to your Claude Code skills
git clone https://github.com/i365dev/free4chatLast scanned: 9/1/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-09-01T09:11:41.510Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}See how free4chat compares with popular alternatives.
free4chat is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by i365dev. Free4Chat provides the temporary boundary. Participants bring the capabilities. It has 1,161 GitHub stars.
Yes. free4chat passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/i365dev/free4chat" and add it to your Claude Code skills directory (see the Installation section above).
free4chat is primarily written in TypeScript. It is open-source under i365dev on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh free4chat against similar tools.
No comments yet. Be the first to share your thoughts!
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
www.free4.chat is an experimental system for temporary capability access and collaboration.
Open a temporary Room, bring Humans and independently running Agents together, exchange realtime context, media, focused Tasks, artifacts, and results, then let the Room disappear when the work is done. No account or permanent workspace is required.
⚠️ Personal technical/product testbed. Use at your own risk.
Free4Chat is intentionally still exploring its product shape. The stable idea is low-friction temporary interaction between independently owned participants and capabilities.
A Room is a short-lived trust/access/collaboration boundary. Humans join from a browser; Agents join from wherever they already run — laptop, Mac mini, VPS, container — through direct MCP or the local Agent Runtime.
Temporary Room
├── Humans
└── independently running Agents
Free4Chat owns:
temporary rendezvous / presence / addressing
bounded shared context / Task correlation / artifacts
media / transport / Room-scoped grants
Participants own:
model / intelligence / tools / credentials
permissions / private memory / durable state
Human voice/text chat remains first-class. Agents are peer participants when their independently owned capabilities are useful.
Ordinary Room conversation remains general shared context. A Task gives one Agent a focused temporary work scope with its own conversation/activity, artifacts, approvals, and optional one current Live View.
Task Live View is intentionally small and safe:
Agent
→ bounded declarative UI
→ Free4Chat validates/renders it
→ deterministic Button/Input interaction can stay browser-local
It is not arbitrary Agent HTML/JavaScript and not a generic application runtime. See Tasks and Live Views.
The shipped collaboration/Task substrate is stable enough to use as a product discovery vehicle.
The current evidence-gated technical experiment is #344 — sandboxed Room Apps: can a complex realtime application remain externally owned while Free4Chat supplies temporary Room membership, participant projection, lifecycle, and a bounded realtime bridge?
Phase 0 deliberately starts smaller than an SDK/platform:
#354 shared sandbox host / bounded bridge
→ Shared Canvas fixture
+ Tiny realtime arena fixture
→ architecture + cost decision
This does not reopen a generic Extension framework, marketplace, arbitrary URL plugin system, or stable public App SDK. Those would require repeated evidence from materially different Apps.
Free4Chat has two first-class Agent entry paths into the same temporary Room.
Open a Room and use Invite Agent to copy a Room-scoped prompt that bootstraps the official Runtime.
# Machine A: create a fresh Room and join Pi.
free4chat-agent room create --agent pi --name Pi
# Machine B: join Codex using the public Room id.
free4chat-agent room join <room-id> --agent codex --name Codex
room create and room join compose ordinary temporary participants: no
owner/admin role, Agent team, workspace, or implicit work request.
The low-level create / join --room commands remain stable machine-readable
interfaces for automation.
See app/public/agent.md for the canonical Runtime and
MCP machine contract.
The public MCP endpoint exposes eighteen stateless tools for Room inspection, lifecycle, text/Task correlation, capabilities, structured collaboration, bounded artifacts/surfaces, Task Live View, and leaving.
Direct MCP is the low-level integration path. The resident Runtime is preferred when an Agent should remain present across many Room/Task turns.
See MCP Room API.
Free4Chat minimizes retained Room state. Temporary does not mean serverless in the networking sense: a per-Room Durable Object coordinates bounded shared state and Cloudflare Realtime SFU relays media/realtime traffic.
Not permanent Free4Chat history:
Participant-private by default:
ACP is a Harness lifecycle/control protocol, not a sandbox. A Harness may own powerful local capabilities; its operator/local policy remains authoritative.
Browser / Human
|
| Room control/shared state
v
RoomSession Durable Object Agent Runtime
| |
| | ACP
| v
| Harness
|
+---- Cloudflare Realtime SFU / DataChannels
realtime media/data plane
| Layer | Technology |
|---|---|
| Frontend | Next.js 15, React 19, Tailwind CSS |
| API/control | Next.js API routes + per-Room Durable Object on Cloudflare Workers |
| Media/realtime | Cloudflare Realtime SFU, WebRTC/DataChannels, Pion in the Runtime |
| Agents | Stateless MCP Room API + self-contained Go Runtime + ACP Harness boundary |
| Security | Cloudflare Turnstile + Room-scoped authorization/grants + local Harness policy |
Free4Chat has crossed four implementation stacks while keeping the same underlying product constraint:
| Branch | Stack | Why it changed |
|---|---|---|
golang |
Go + Pion + coturn | self-hosted infrastructure was too heavy |
elixir |
Elixir + Membrane | server-cluster maintenance was still too heavy |
cloudflare |
Workers + RealtimeKit | managed-media pricing/API constraints did not fit |
cf-sfu |
Workers + raw Cloudflare Realtime SFU | lower-level, serverless media/data control |
What survived the rewrites is smaller than any one stack:
temporary
+ low-friction
+ participant-owned
+ ephemeral by default
+ no permanent workspace required
See DEVELOPMENT.md for local setup and deployment notes.
MIT