tantra
The agent actor runtime as a Python library. Install name tantra-harness, import name tantra.
Tantra gives each agent a durable FIFO inbox, an independent event journal, and one active turn. A process-wide Runtime owns providers, stores, tools, hooks, permissions, skills, memory, compaction, telemetry, actor tasks, and writer connections.
Install
| Command | Adds |
|---|---|
pip install tantra-harness |
Core runtime and shell tools |
pip install "tantra-harness[web]" |
Brave web search and web fetch |
pip install "tantra-harness[doc]" |
PDF and Word document reading |
pip install "tantra-harness[postgres]" |
PostgreSQL storage |
pip install "tantra-harness[telemetry]" |
OpenTelemetry tracing |
The unrelated PyPI project tantra installs the same import name. Do not install both projects in one environment.
Basic usage
import asyncio
from uuid import uuid4
from tantra import Agent, OpenAICompatible, Runtime, SQLiteStore
from tantra.extratools.web import web_search
class Researcher(Agent):
model = "gpt-5"
prompt = "Answer with current, sourced information."
tools = [web_search(api_key=BRAVE_API_KEY)]
async def main() -> None:
store = SQLiteStore("sessions.db")
await store.setup()
runtime = Runtime(
OpenAICompatible("https://api.openai.com/v1", OPENAI_API_KEY),
store,
[Researcher],
)
root_id = await runtime.create(Researcher)
async with runtime.connect(root_id, writable=True) as connection:
result = await connection.prompt(
"What changed in Python 3.13?",
command_id=uuid4(),
)
print(result.text)
await runtime.aclose()
asyncio.run(main())
Connection.prompt() accepts a durable command and waits for its terminal result. For streaming, call send() and iterate the connection. Reconnect with the last scalar seq as after; use Runtime.events() for a child journal. Command IDs are UUIDs and make acceptance idempotent.
Subagents are independent actors. Models use the injected spawn, status, send, and finish tools; no parent stream merges child events. Plain completion leaves a child reusable and notifies its parent with status only, while finish delivers the final result. Human asks and approval-gated tools are root-only.
Compaction is opt-in with Runtime(compactor=PruneThenSummarize()). Configured runtimes budget the complete provider request, preserve system and tool definitions, and compact each actor independently.
For multi-process deployments, pair PostgresStore with the optional PostgresCoordinator for leased execution ownership, fenced writes, command forwarding, and takeover recovery. The default remains single-process.
Tantra 1.4 reduces active PostgreSQL runtime CPU with bounded durable delta batching, terminal-aware result checks, shared recent event pages, and focused actor observation. Full history remains the default, and public replay stays complete. Stop PostgreSQL writers before upgrading an existing database; the root-key migration rewrites session rows.
See the documentation, the 1.4 upgrade guide, and the coordinator setup guide.
Reference app
apps/sarathi is the repository's interactive web application.
License
Apache-2.0
Metadata
Release files for tantra-harness 1.4.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| tantra_harness-1.4.0.tar.gz | 302.4 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| tantra_harness-1.4.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 437.1 kB
Release files / tantra_harness-1.4.0.tar.gz
| Download URL | tantra_harness-1.4.0.tar.gz |
|---|---|
| Size | 302.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
bad4833e4737d00c5c7010dc623be8d1e71374da5d9f7aa63bd6e9b220c7c8af
|
|
BLAKE2b-256 checksum How to use checksums |
d9007099158e1ef49375d97baf05837038178101bcbd8e1fc83cfe503f6bdce0
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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 Oct 4, 2026.
Transparency logRelease files / tantra_harness-1.4.0-py3-none-any.whl
| Download URL | tantra_harness-1.4.0-py3-none-any.whl |
|---|---|
| Size | 134.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
e96c2b3674e06c5dbb4bcec7a6b1c30b04bcbe0826007dd52eae30ca171c3867
|
|
BLAKE2b-256 checksum How to use checksums |
b4829bb6170c983554269ff7074b98c354b60d768744f68038f20939bf3ff177
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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 Oct 4, 2026.
Transparency log