Skip to main content
Pre-release

This release is a pre-release and may not be stable for production use.

neosian

neosian

PyPI Docs CI License: Apache-2.0 Python 3.12 | 3.13 | 3.14

The state layer for LLM agents: durable conversations, agent-curated memory, skills, a shared board and a ledger of who did what — on storage you own (a directory, your Postgres, or one small state process), for the agent you already use or the one you build.

Two doors, one store:

  • Build an agent. An async-only, stateless Agent (tools, streaming, fallback, guardrails, structured output) that a Conversation wraps into a durable, memory-bearing thread.
  • Give your agent state. Claude Code, Codex, Cursor or OpenCode get memory and skills over MCP and every session recorded through hooks — neosian setup --write wires every client it finds; neosian status says whether the machine is set up; bare neosian opens a chat with an agent that knows neosian, on the same memory.

neosian record install writes the hooks; one headless Claude Code session lands as a recorded turn; neosian audit names it
The next Claude Code session opens on where we left off and answers from the record

A Claude Code session landing as a recorded turn that neosian audit names, and the next session opening on where we left off — no key of yours, no flags: the home and this project's scope.

Agents read this repository too: llms.txt is the machine front door, neosian docs prints the shipped docs pages from the wheel (version-true), and every shell verb has --json and exit tiers — one CLI for humans and agents (neosian docs cli).

store = FileStore(home())                          # ~/.neosian, or your PostgresStore(dsn)
convo = Conversation(config, store=store, conversation_id="thread-829",
                     memory_scope=project_scope())  # user:<login>/proj:<dir>
response = await convo.send("Where did we leave off?")

Install

Requires Python >= 3.12. One package, everything in it — on PyPI as a pre-release until v1.0.0, so pin it:

uv add "neosian==1.0.0rc11"

The install brings the library with its two provider SDKs (OpenAI and Anthropic — Cerebras, xAI and Gemini ride the OpenAI wire), the neosian shell, the MCP server and client, the state process and OpenTelemetry spans: about 70 MB on disk, none of it loaded until used. Nothing in it needs an account or a server to start — Model.FAKE runs keylessly and FileStore is a directory. The one extra is the Postgres driver, uv add "neosian[postgres]==1.0.0rc11", for a PostgresStore against a server you already run; [all] is its alias, and the former [cli], [mcp], [otel] and [server] still resolve for one release and add nothing.

For a machine with nothing on it, the one-liner is scripts/install.sh: it says what it installs, finds uv or installs it from a pinned release, runs uv tool install neosian, checks the PATH and prints the registration command. It is the same two commands, spelled out beside it:

curl -fsS https://neosian.com/install | bash
# or, by hand:
curl -LsSf https://astral.sh/uv/install.sh | sh
uv tool install "neosian==1.0.0rc11"

To work on neosian itself, uv sync --all-groups then uv run neosian version (the Development section has the gates).

Quickstart

Keyless boot is an invariant: Model.FAKE is always available, so an install verifies with no account. The fake is scripted through the client_factory seam — the same seam the unit tier and the eval baseline use:

import asyncio

from neosian import Agent, AgentConfig, Message, Model, Role
from neosian.fake import FakeClient, FakeScript, FakeTurn

fake = FakeClient(FakeScript(turns=(FakeTurn(content="hello from the fake"),)))
config = AgentConfig(system_prompt="Be concise.", model=Model.FAKE,
                     client_factory=lambda _: fake)


async def main() -> None:
    response = await Agent(config=config).run(
        [Message(role=Role.USER, content="hello")], stream=False
    )
    print(response.message.content)


asyncio.run(main())

Set a key and name a real model (model=Model.CLAUDE_SONNET_5, the providers table below); tools are decorated functions whose signature is the schema (neosian docs tools). examples/ has one runnable file per feature, every one importing keylessly.

What is in the box

Each line is one page in the wheel — neosian docs <topic>.

  • Conversation and memory (memory). History is an append-only log; log-projection compaction pages aged turns out of context and recall_turn re-hydrates any of them verbatim — paging, not deletion. Memory is file-school: small markdown documents with frontmatter under mounted scopes, read and written through one memory tool (view, create, str_replace, insert, delete, rename); reflection at the close distills the session into deliberate writes. Every write is a full-content version row with an actor; a memory_write frame on the stream carries {command, path, version} so a host renders "remembered X" with a working revert_memory undo.
  • The shell and the ledger (cli). The six memory commands, the gardener (maintain), the operator verbs (versions, redact, revert), audit — what was done, by whom, when, on any substrate — and export/import, which move a store whole, history included.
  • Skills (skills). A skill is a document under skills/<name> in a mount: versioned, curated by the mount flag, loaded by list_skills/load_skill, served over MCP as a prompt (a slash command in Claude Code).
  • MCP, both directions (mcp). python -m neosian.mcp serves the store to any client over stdio; McpServer.stdio/http/in_process consumes any MCP server as agent tools — schema verbatim, is_error in-band, the approval gate and hooks unchanged.
  • The agent you already use (agents). neosian record install spells the hooks that land a prompt-to-stop span as one turn by claude-code:<session> (Codex and OpenCode too), plus a sessions document; SessionStart prints the index and "where we left off" into the next window. A neosian Conversation on the same home shares the scope, so one audit names both.
  • The state process (topology). neosian serve puts memory and conversations on a port (the shipped Dockerfile is the appliance) — reach, not capability; RemoteStore drops in where FileStore does, core install. Bearer tokens env-only, per-client when you want the ledger to know who wrote.
  • The agent core (agent, tools). run(stream=True) yields ten frozen AgentEvent dataclasses a host relays over SSE; AgentHooks observe every turn, call and tool; ToolGateConfig routes every tool call through one approver, and no decision is a denial; capability- aware fallback, guardrails on any model, structured output, prompt caching, multimodal blocks on Anthropic.

Providers

API keys are read from environment variables; a provider is available when its key is set (asking for an unavailable model raises MissingAPIKeyError).

Provider Env var Models
A registered door the door's api_key_env The day-one door for any model neosian has not shipped: any OpenAI-compatible endpoint via register_model (neosian docs quickstart)
OpenAI OPENAI_API_KEY gpt-5.6-sol (default), gpt-6-astra, gpt-5.6-terra, gpt-5.6-luna, gpt-5.1 (reasoning, max effort), on the Responses API with reasoning carried through tool loops and nothing stored at the provider
Anthropic ANTHROPIC_API_KEY claude-fable-5-1, claude-opus-5, claude-sonnet-5 (default); vision/PDF input, prompt caching, adaptive thinking
Cerebras CEREBRAS_API_KEY Default provider: gpt-oss-120b, qwen-3.8-27b
xAI XAI_API_KEY grok-4.6 — a shipped door row (Model.GROK_4_6), on the Responses API
Google Gemini API GEMINI_API_KEY gemini-3.8-flash, gemini-3.7-flash on the OpenAI-compatible endpoint (Model.GEMINI_3_8_FLASH; the introductory card through 2026-12-31)
Moonshot MOONSHOT_API_KEY kimi-k3: a shipped door row (Model.KIMI_K3), always reasoning
Fake — Keyless, deterministic, always available (Model.FAKE)

Every shipped row is a Model member and answers to its wire id too (AgentConfig(model="gpt-5.6-sol")); each carries its provider's lifecycle as data (Model.X.spec.retires, card_until) and is earned by green dispatched runs of the memory baselines — membership is measured, never assumed (neosian docs baselines).

Storage

MemoryStore and ConversationStore are the contracts: async ABCs that own no connection, commit no transaction, issue no DDL. FileStore (a plain directory), PostgresStore (the postgres extra; schema by python -m neosian.schemas postgres | psql "$DSN") and RemoteStore (the state process's wire) implement both; a host may implement its own, kept honest by the shipped MemoryStoreContract / ConversationStoreContract conformance kits. One writer per FileStore root; many workers on one Postgres.

Evaluation

neosian eval suite.yaml runs YAML suites and exits nonzero on failure — an agent suite over variants × models × cases, and kind: memory, which scores store truth across scripted sessions on every transport. The shipped memory pack is all-green on models: [fake], and the same pack against the real providers produces the baselines page, fingerprint-gated so a prompt change without a recorded re-run fails make test.

Stability

v1.0.0 is deliberately not yet cut. When it is, it will carry the API stability promise: Agent, Conversation, MemoryStore, and the neosian.evaluation facade stable under SemVer, the ecosystem seams (scope grammar, token classes, integer micro-USD, event vocabulary, error codes) SemVer-guaranteed — a seam break only at a major — and the state process's wire (the twelve /v1/ store routes and their envelope, versioned by WIRE_VERSION) stable under the same promise: one promise covering library, seams, and wire. Until then the seams are append-only by convention, and error codes are already append-only forever. Consumers pin a release (neosian==X.Y.Z), never master. Model ids follow their providers' lifecycles: a retired id leaves in the next release after its provider's date, named in the changelog; each shipped row's clock is data on its spec (neosian docs baselines).

Development

make install    # uv sync --locked --all-groups
make lint       # ruff + black --check + import-linter
make typecheck  # mypy --strict neosian tests examples
make test       # unit tier — the default gate, zero API keys
make size       # file-size gate (warn 300 / fail 500)
make test-external provider=anthropic file=~/path/to/creds  # real API calls
make test-postgres                                      # needs NEOSIAN_TEST_POSTGRES_DSN
make test-container                                     # both kits vs the container (docker)

The default gate needs no accounts; external tiers inject credentials value-blind. Sign off every commit (git commit -s): contributions are accepted under the Developer Certificate of Origin and licensed as the project is, Apache-2.0 — there is no CLA. Open an issue before a feature or a departure from documented behaviour; the public API is pinned by tests/unit/test_init.py, so an export change is a reviewed diff. SECURITY.md is where vulnerabilities go, never an issue.

Documents

  • neosian docs <topic> — the shipped pages, from the wheel: quickstart, agent, tools, memory, skills, cli, mcp, agents, topology, baselines (the published per-provider memory numbers); the same pages online at docs.neosian.com, rendered from the wheel at the current release.
  • SERVICES.md — every env key and what turning it off means.
  • CHANGELOG.md — Keep a Changelog, one section per release.
  • SECURITY.md — where to report, and the supported line.
  • llms.txt — the machine-readable front door (byte-identical twin ships in the wheel).

Be kind and constructive in every project space; the maintainers read community@neosian.com.

Metadata

Release files for neosian 1.0.0rc11

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for neosian 1.0.0rc11
File Size Uploaded Provenance
neosian-1.0.0rc11.tar.gz 992.6 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for neosian 1.0.0rc11
File Interpreter ABI Platform
neosian-1.0.0rc11-py3-none-any.whl Python 3 none any Details

Total release size: 1.6 MB

Release files / neosian-1.0.0rc11.tar.gz

Download URL neosian-1.0.0rc11.tar.gz
Size 992.6 kB
Tags Source
SHA-256 checksum
How to use checksums
eba78f310ffb06ee6d94dbefd9558ebd2c5b0c608ebaf61fd3768071accc0a84
BLAKE2b-256 checksum
How to use checksums
13e6204708d6e0e3ab13678aef89b17a18ff8381e2408609a5b418d4edccec6d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via uv/0.12.10 {"installer":{"name":"uv","version":"0.12.10","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 / neosian-1.0.0rc11-py3-none-any.whl

Download URL neosian-1.0.0rc11-py3-none-any.whl
Size 597.2 kB
Tags Python 3
SHA-256 checksum
How to use checksums
080808d5400f56725dc10a8f1cecc670651c614094626d7042c9cd108643a4ff
BLAKE2b-256 checksum
How to use checksums
05438ca37f2f575ac29d2180c5fb9e9769b929f88058379baef497b0fa2ac6c2
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via uv/0.12.10 {"installer":{"name":"uv","version":"0.12.10","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 neosian 1.0.0rc11

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.

Release history Release notifications | RSS feed

This release
Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page