molecule-ai/molecule-core
51
0
Fork 2
Code Issues 163 Pull Requests 155 Actions 18 Packages Projects Releases Wiki Activity

PR #3033: docs(README): add codex to runtime list and compatibility table #2054

Closed
core-be wants to merge 4 commits from pr-3033 into staging
pull from: pr-3033
merge into: molecule-ai:staging
Conversation 0 Commits 4 Files Changed 2
+6 -15
2 changed files with 6 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+6 -6
View File
@@ -53,7 +53,7 @@ Molecule AI is the most powerful way to govern an AI agent organization in produ
It combines the parts that are usually scattered across demos, internal glue code, and framework-specific tooling into one product:
- one org-native control plane for teams, roles, hierarchy, and lifecycle
- one runtime layer that lets **eight** agent runtimes — LangGraph, DeepAgents, Claude Code, CrewAI, AutoGen, **Hermes**, **Gemini CLI**, and OpenClaw — run side by side behind one workspace contract
- one runtime layer that lets **nine** agent runtimes — LangGraph, DeepAgents, Claude Code, CrewAI, AutoGen, **Hermes**, **Gemini CLI**, OpenClaw, and **Codex** — run side by side behind one workspace contract
- one memory model that keeps recall, sharing, and skill evolution aligned with organizational boundaries (Memory v2 backed by pgvector for semantic recall)
- one operational surface for observing, pausing, restarting, inspecting, and improving live workspaces
@@ -75,7 +75,7 @@ You do not wire collaboration paths by hand. Hierarchy defines the default commu
### 3. Runtime choice stops being a dead-end decision
LangGraph, DeepAgents, Claude Code, CrewAI, AutoGen, Hermes, Gemini CLI, and OpenClaw can all plug into the same workspace abstraction. Teams can standardize governance without forcing every group onto one runtime.
LangGraph, DeepAgents, Claude Code, CrewAI, AutoGen, Hermes, Gemini CLI, OpenClaw, and Codex can all plug into the same workspace abstraction. Teams can standardize governance without forcing every group onto one runtime.
### 4. Memory is treated like infrastructure
@@ -120,6 +120,7 @@ Molecule AI is not trying to replace the frameworks below. It is the system that
| **Hermes 4** | Shipping on `main` | Hybrid reasoning, native tools, json_schema (NousResearch/hermes-agent) | Option B upstream hook, A2A bridge to OpenAI-compat API, multi-provider provider derivation |
| **Gemini CLI** | Shipping on `main` | Google Gemini CLI continuity | Workspace lifecycle, A2A, hierarchy-aware collaboration, shared ops plane |
| **OpenClaw** | Shipping on `main` | CLI-native runtime with its own session model | Workspace lifecycle, templates, activity logs, topology-aware collaboration |
| **Codex** | Shipping on `main` | OpenAI Codex CLI continuity | Workspace lifecycle, A2A, hierarchy-aware collaboration, shared ops plane |
| **NemoClaw** | WIP on `feat/nemoclaw-t4-docker` | NVIDIA-oriented runtime path | Planned to join the same abstraction once merged; not yet part of `main` |
This is the key idea: **many agent runtimes, one organizational operating system**.
@@ -209,7 +210,7 @@ The result is not just “an agent that learns.” It is **an organization that
### Runtime
- unified `workspace/` image; thin AMI in production (us-east-2)
- adapter-driven execution across **8 runtimes** (Claude Code, Hermes, Gemini CLI, LangGraph, DeepAgents, CrewAI, AutoGen, OpenClaw)
- adapter-driven execution across **9 runtimes** (Claude Code, Hermes, Gemini CLI, LangGraph, DeepAgents, CrewAI, AutoGen, OpenClaw, Codex)
- Agent Card registration
- awareness-backed memory integration; **Memory v2 backed by pgvector** for semantic recall
- plugin-mounted shared rules/skills
@@ -239,7 +240,6 @@ The result is not just “an agent that learns.” It is **an organization that
- no tunnel, no public endpoint — the plugin self-registers each watched workspace as `delivery_mode=poll` and long-polls `/activity?since_id=…`
- multi-tenant friendly: one plugin install can watch workspaces across multiple Molecule tenants (`MOLECULE_PLATFORM_URLS` per-workspace)
- install via the standard marketplace flow: `/plugin marketplace add Molecule-AI/molecule-mcp-claude-channel` → `/plugin install molecule-channel@molecule-mcp-claude-channel`
## Built For Teams That Need More Than A Demo
Molecule AI is especially strong when you need to run:
@@ -260,7 +260,7 @@ Canvas (Next.js 15, warm-paper :3000) <--HTTP / WS--> Platform (Go 1.25 :8080)
+------------------------- shows ------------------------> workspaces, teams, tasks, traces, events
Workspace Runtime (Python ≥3.11, image with adapters)
- 8 adapters: LangGraph / DeepAgents / Claude Code / CrewAI / AutoGen / Hermes / Gemini CLI / OpenClaw
- 9 runtimes: LangGraph / DeepAgents / Claude Code / CrewAI / AutoGen / Hermes / Gemini CLI / OpenClaw / Codex
- Agent Card + A2A server (typed-SSOT response path, RFC #2967)
- heartbeat + activity + awareness-backed memory (Memory v2 — pgvector semantic recall)
- skills + plugins + hot reload
@@ -328,7 +328,7 @@ Then open `http://localhost:3000`:
## Current Scope
The current `main` branch ships the core platform, Canvas v4 (warm-paper themed), Memory v2 (pgvector semantic recall), the typed-SSOT A2A response path (RFC #2967), **eight production adapters** (Claude Code, Hermes, Gemini CLI, LangGraph, DeepAgents, CrewAI, AutoGen, OpenClaw), skill lifecycle, and operational surfaces.
The current `main` branch ships the core platform, Canvas v4 (warm-paper themed), Memory v2 (pgvector semantic recall), the typed-SSOT A2A response path (RFC #2967), **nine production runtimes** (Claude Code, Hermes, Gemini CLI, LangGraph, DeepAgents, CrewAI, AutoGen, OpenClaw, Codex), skill lifecycle, and operational surfaces.
The companion private repo [`molecule-controlplane`](https://git.moleculesai.app/molecule-ai/molecule-controlplane) provides the SaaS surface — multi-tenant orchestration on EC2 + Neon + Cloudflare Tunnels, KMS envelope encryption, WorkOS auth, Stripe billing, and a `tenant_resources` audit table with a 30-min reconciler.
workspace-server/internal/handlers/a2a_proxy_helpers.go
-9
View File
@@ -407,15 +407,6 @@ func validateCallerToken(ctx context.Context, c *gin.Context, callerID string) e
// matching (the wsauth errors are typed for the invalid case).
var errInvalidCallerToken = errors.New("missing caller auth token")
// canvasUserMessage holds the extracted user message extracted from an
// A2A canvas request body for broadcasting to other sessions.
type canvasUserMessage struct {
Message string `json:"message,omitempty"`
Parts []map[string]interface{} `json:"parts,omitempty"`
MessageID string `json:"messageId,omitempty"`
Attachments []map[string]interface{} `json:"attachments,omitempty"`
}
// extractCanvasUserMessage parses an A2A JSON-RPC request body and extracts
// the user-authored text and attachments from a canvas-initiated message/send.
// Returns nil when the body is not a canvas user message (empty, malformed,