This project has been archived by its maintainers, and is no longer receiving any updates.
Helix — Self-Improving AI Agent
Helix is a self-improving AI agent with persistent memory, a skills system, tool calling, MCP integration, and multiple interfaces: CLI, TUI, API gateway, and Telegram.
Website: helix-agent.ru · PyPI: HelixAgentAi · GitHub: javded-itres/HelixAgent · Telegram: @helix_agent · Docs: EN · RU · Donate: Boosty
Features
- Tool calling — files, shell, web, code execution, optional Playwright browser tools
- Persistent memory — SQLite conversations + ChromaDB semantic search
- Skills — markdown skills with auto-generation and hub catalogs (ClawHub, Hermes, Claude plugins)
- MCP — configure and assign Model Context Protocol servers per agent
- Multi-provider — Ollama, LiteLLM, OpenAI, Groq, and any OpenAI-compatible API
- Interfaces —
helix tui,helix chat-command,helix run,helix gateway - Security — API keys, rate limits, command whitelist, confirmation prompts
- Operations —
helix doctor,helix logs, background gateway supervisor, Docker
Quick start
Install
Install from PyPI (Python 3.12+). Package: HelixAgentAi, CLI command: helix:
pipx install HelixAgentAi # global CLI (recommended)
pipx install "HelixAgentAi[all]" # + telegram, browser, tui-web, voice
# or in a virtualenv:
pip install HelixAgentAi
pip install "HelixAgentAi[telegram,browser]"
Do not use pip install helix — that is a different package on PyPI.
Update later: helix update --channel pypi
From source (developers):
git clone https://github.com/javded-itres/HelixAgent.git
cd HelixAgent
./scripts/install.sh # macOS / Linux
# Windows: .\scripts\install.ps1
helix version
helix doctor
Publishing: docs/en/PYPI.md
Developer install:
uv sync && uv pip install -e .
cp .env.example .env
Full guide: docs/en/INSTALLATION.md
Configure and run
helix models setup
helix tui # recommended UI
# or:
helix chat-command
helix run "What is in this repo?"
helix gateway start
Documentation (English)
| Topic | Link |
|---|---|
| Install & update | INSTALLATION.md |
| CLI reference | CLI.md |
Slash commands / |
SLASH_COMMANDS.md |
| TUI | TUI.md |
| Configuration | CONFIGURATION.md |
| Skill Hub | HUB.md |
| API Gateway | GATEWAY.md |
| Logs | LOGS.md |
| Doctor | DOCTOR.md |
| Security | SECURITY.md |
| Deployment | DEPLOYMENT.md |
| Troubleshooting | TROUBLESHOOTING.md |
| Architecture | ARCHITECTURE.md |
Документация (русский)
| Тема | Ссылка |
|---|---|
| Установка | INSTALLATION.md |
| CLI | CLI.md |
| Слэш-команды | SLASH_COMMANDS.md |
| Начало | START_HERE.md |
CLI at a glance
helix tui # main UI
helix run "query" # one-shot
helix models setup # providers
helix hub browse # external skills
helix mcp setup # MCP servers
helix gateway start|status|stop|reload
helix logs [-s agent] [-f]
helix doctor [--fix]
helix install | helix update
In TUI/Telegram, type /help for slash commands. See docs/en/SLASH_COMMANDS.md.
Architecture
HelixAgent → run_agent_loop() (core/agent_execution.py)
→ LangGraph / AgentLoop
| Layer | Path |
|---|---|
| Execution | core/agent_execution.py |
| Events | core/agent_events.py |
| Tools | core/tools/ |
| Memory | core/memory/ |
| CLI | cli/main.py |
| Gateway | api/gateway.py |
Details: docs/en/ARCHITECTURE.md
Docker
docker compose up -d
Contributing
See CONTRIBUTING.md. Run tests before PRs: uv run pytest -m "not llm".
License
MIT — see LICENSE
Metadata
Release files for HelixAgentAi 0.1.8
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 | |
|---|---|---|---|---|
| helixagentai-0.1.8.tar.gz | 1.3 MB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| helixagentai-0.1.8-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 2.9 MB
Release files / helixagentai-0.1.8.tar.gz
| Download URL | helixagentai-0.1.8.tar.gz |
|---|---|
| Size | 1.3 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
b358cd1b81151b1a74373d913df310d1fa372e2028b553ef28605fdcbea2f141
|
|
BLAKE2b-256 checksum How to use checksums |
920282c582b80a06dd9e8b86802d2d7339c95c008f2253b1d70f79fc715ea7d9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.11.20 {"installer":{"name":"uv","version":"0.11.20","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Release files / helixagentai-0.1.8-py3-none-any.whl
| Download URL | helixagentai-0.1.8-py3-none-any.whl |
|---|---|
| Size | 1.5 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
026ee28a095eb2d3de5b5e990876a13f0b4c5c1e90b48edb8ba3aab600953149
|
|
BLAKE2b-256 checksum How to use checksums |
265bd566bee4f1bd0f32ce1fd6f0956b19b573e772095329d4d943a72d3702e7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.11.20 {"installer":{"name":"uv","version":"0.11.20","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Security for HelixAgentAi 0.1.8
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.