Cortex
Personal Agent Infrastructure Stack
One person. Infinite agents.
Cortex is four integrated systems that let a single person command, orchestrate, create tools, and capture wisdom — all through AI agents.
The Stack
| Component | Role | Description |
|---|---|---|
| Dispatcher | Command | Mobile JARVIS via Telegram. Always-on daemon. Zero dependencies. |
| A2A Hub | Communication | Agent-to-Agent protocol. WebSocket hub + MCP bridge for Claude Code. |
| Forge | Creation | Self-evolving tool agent. Describe → Clarify → Generate → Test → Install. |
| Vibe Replay | Memory | Capture sessions, extract learnings, generate shareable replays. |
Architecture
┌─────────────────────────────┐
│ YOU (Phone / Desktop) │
└──────────────┬──────────────┘
│
┌──────────────▼──────────────┐
│ DISPATCHER (Command) │
│ Classify → Route → Execute │
└──────┬───────────┬──────────┘
│ │
┌─────────▼───┐ ┌────▼──────────┐
│ A2A HUB │ │ FORGE │
│ (Comms) │◄►│ (Creation) │
└──────┬──────┘ └───────────────┘
│
┌──────────▼─────────────────────────┐
│ VIBE REPLAY (Memory) │
│ Capture → Analyze → Share Wisdom │
└────────────────────────────────────┘
Quick Start
# Each component installs independently
pip install a2a-hub forge-agent vibe-replay
# Start the agent communication hub
a2a-hub start
# Create a tool from natural language
forge create "convert CSV to JSON with filtering"
# Capture and replay coding sessions
vibe-replay install # Hook into Claude Code
vibe-replay replay latest
Philosophy
We believe AI agents should be like utilities — always on, working for you, learning and improving. Cortex is built by one person who uses it daily to run a research lab, ship open-source projects, and automate everything in between.
The best tools don't just help you do things faster. They change what's possible for one person to do.
Website
Open index.html or visit the GitHub Pages site for the full interactive documentation.
Stats
- 4 integrated systems
- 141 tests passing
- 0 external dependencies (Dispatcher)
- 1 person needed
License
MIT — see individual component repos for details.
Built by one person and their AI agents. Naturally.
Metadata
Release files for cortex-cli-agent 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| cortex_cli_agent-0.1.1.tar.gz | 139.1 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| cortex_cli_agent-0.1.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 172.1 kB
Release files / cortex_cli_agent-0.1.1.tar.gz
| Download URL | cortex_cli_agent-0.1.1.tar.gz |
|---|---|
| Size | 139.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
42a188cbabd46bf0adbe39e137552e53adfa0850072af33bcba69420b0078c63
|
|
BLAKE2b-256 checksum How to use checksums |
357d596a79fb262e4de52fa886b625d94491be4fe5b583bd7c0e8dbf4708754a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.9.6
|
Release files / cortex_cli_agent-0.1.1-py3-none-any.whl
| Download URL | cortex_cli_agent-0.1.1-py3-none-any.whl |
|---|---|
| Size | 33.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
d525facc3be8a3eacab9aa181c7e87e46bf981ffe4906798ddf040462f2a27b7
|
|
BLAKE2b-256 checksum How to use checksums |
a8b070ca3312944fe2b2ab91fa93c8642e846e96786a01353bad15f562a6b49b
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.9.6
|
Security for cortex-cli-agent 0.1.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.