superpos-agent-core
Shared runtime for the Superpos "slim agent" family — the part that is identical across Claude, Codex, Gemini, Qwen, and any future LLM-CLI-backed agent.
What lives here
Executorprotocol +ExecutionRequest— the contract every agent implementation must satisfy.SuperposClient— REST client for the Superpos backend (tasks, persona, agent lifecycle).run_superpos_poller— daemon that polls Superpos for tasks and enqueues them on anExecutor.TelegramGateway+TelegramStreamer+build_telegram_app/run_telegram_bot— Telegram I/O with backpressure, flood-ban handling, message streaming.WorktreeManagerhelpers — per-branch isolation viagit worktree.SessionStore,RecentTasksLog,RuntimeConfig— persistence and runtime knobs.redact()— strip known secret patterns from outbound text.run_agent()— orchestrator that wires everything together given a concreteExecutorfactory.
What does NOT live here
- Per-agent executor implementations (
ClaudeExecutor,CodexExecutor,GeminiExecutor, …) — they live in each agent's own repo and depend on this package. - LLM SDK / CLI installation — each agent's Dockerfile is responsible.
- Per-agent config (model lists, auth env vars) — subclassed from
BaseConfig.
Using it
from superpos_agent_core import run_agent, BaseConfig, Executor
class MyAgentConfig(BaseConfig):
my_api_key: str = ""
class MyExecutor:
# implements superpos_agent_core.Executor
...
if __name__ == "__main__":
import asyncio
config = MyAgentConfig.from_env(extra={"my_api_key": "MY_API_KEY"})
asyncio.run(run_agent(
config=config,
executor_factory=lambda cfg, runtime, superpos, gateway, persona:
MyExecutor(cfg, runtime, superpos, gateway, persona=persona),
))
See Slim-Agent-Gemini/ for a complete working example.
CLI helpers
superpos_task.py ships a superpos-task console helper agents shell out to
for task/schedule operations. Hive, base URL and token are resolved from the
standard SUPERPOS_* environment variables.
superpos-task create --prompt …— create a task (broadcast by default;--self-targetpins it to the calling agent).superpos-task schedule …— create a one-off / interval / cron schedule.superpos-task schedules/delete-schedule --id …— manage schedules.superpos-task list [filters]— list tasks in the hive. All filters are AND-combined server-side and optional:--status,--type,--target-agent-id,--target-capability,--creator-id,--parent-task-id,--created-after,--created-before,--q, plus--page/--per-page(max 100). Prints a compact summary by default, or the rawdatalist as JSON with--json. (ConsumesGET /api/v1/hives/{hive}/tasks, exposed in the SDK asSuperposClient.list_tasks.)superpos-task show <task-id> [--json]— show a single task by ID (GET /api/v1/hives/{hive}/tasks/{task}, SDKSuperposClient.get_task).superpos-task memory --content … [--mode append|prepend|replace]— update the active persona's MEMORY document.
Metadata
Release files for superpos-agent-core 0.1.15
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 | Actions |
|---|---|---|---|---|
| superpos_agent_core-0.1.15.tar.gz | 286.6 kB | With provenance | Details for superpos_agent_core-0.1.15.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| superpos_agent_core-0.1.15-py3-none-any.whl | Python 3 | none | any | Details for superpos_agent_core-0.1.15-py3-none-any.whl |
Total release size: 498.0 kB
Release files / superpos_agent_core-0.1.15.tar.gz
| Download URL | superpos_agent_core-0.1.15.tar.gz |
|---|---|
| Size | 286.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
5daa1f702594fd477bcc10553214a39d582fc867a72185550a31955a0ccb1d10
|
|
BLAKE2b-256 checksum How to use checksums |
90c063e0eeaccd7c3d377c10bc15993a8add90720e708d1a94b453d1998d5882
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 12, 2026.
Transparency logRelease files / superpos_agent_core-0.1.15-py3-none-any.whl
| Download URL | superpos_agent_core-0.1.15-py3-none-any.whl |
|---|---|
| Size | 211.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
daf0e911f556e3fea92da4ead75629e4412638d3e7d2b67b78354bbe82bf91bd
|
|
BLAKE2b-256 checksum How to use checksums |
6f94cd75fbfb16ddb0de4e588537063bbdcedb289900e23c202942e71d93d5e9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 12, 2026.
Transparency logSecurity for superpos-agent-core 0.1.15
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.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for superpos_agent_core-0.1.15.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 12, 2026.
Transparency logA 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.