HypSwarm

Many agents. One record.
Run one agent or a swarm of them on a research, engineering, trading, knowledge or optimisation task, with a HypGraph record as the only shared state.
hypswarm.com · for agents · the design · decisions · HypGraph

Alpha.

The record schedules the work (orders from its question board), accepts it (predicates the record checks itself), stops what became pointless (premises that fell), re-runs what authors computed (the instrument), and writes the report. Models are called only to do work and to judge exceptions. A solo scientist and an orchestrated swarm are the same program with different seats — and a trading desk, a software team or a research assistant are the same program with a different profile.

import asyncio
from hypswarm import Task, Budget, run
from hypswarm.providers import OpenAICompatible

task = Task(title="Does A beat B",
            mission="Two models were scored on the same items (items.csv). Find out whether A beats B.",
            questions=[("Q1", "What is A's accuracy?"), ("Q2", "Is A significantly better than B?")],
            files={"items.csv": open("items.csv", "rb").read()},
            profile="scientific")                       # or software · trading · knowledge · optimization
model = OpenAICompatible("deepseek-ai/DeepSeek-V4.1-Flash", base_url="https://api.deepinfra.com/v1/openai")
result = asyncio.run(run(task, None, model, record="study.hypgraph", budget=Budget(max_calls=150, max_usd=1.0)))
print(result.report)        # the facts from the record, the lead's interpretation under them, the answers

seats=None takes the profile's roster. Or from the shell: hypswarm run --task task.toml --profile software --record study.hypgraph.

Profiles: what counts, per discipline

A profile is a HypGraph governance profile — what the record will accept and refuse — plus the seats and tools that usually work under it. It is pinned on the investigation and versioned, so a record written under trading@1 means the same thing in a year.

Every profile adds a paragraph of its rules to each seat's preamble and tells the scheduler what "complete" means (completion()); hypswarm profiles lists them. Adding a discipline is a Profile in HypGraph plus a roster here — the scheduler does not change.

Workflows, per profile

The scheduler is the same everywhere; what differs is what each order must produce before the record calls it done, and what the record refuses on the way. Italic steps are mechanical — no model is called.

scientific — question → register_run (run + result + claim, numbers bound) → instrument re-runs the code → review by the critic (judges; recomputes only a contradiction) → question settled → report from the facts, linted. Refused on the way: a number no result accounts for, "never" without the count, "significant" without the test.

software — requirement → the implementer's change as an artifact by hash → register_run with the exact test command as code → instrument runs the tests (a lab run that replicates the tester's: this is tests_pass) → claim "passes", accepted only now → review of method and wording → requirement verified. Refused on the way: "it passes" before the instrument has run.

trading — market question → hypothesis (the thesis and the move it predicts) + experiment (the backtest preregistered: window, costs) → register_run with oos_return, fees, slippage, drawdown (backtested_oos) → instrument re-runs the backtest → review by the risk seat → a decision node: paper position, size, stop, review date, based_on the claim → position recorded. Refused on the way: a backtest without the costs it charged, "edge" from the fitting window, any live order (there is no path).

knowledge — question → read through an allowlisted fetch tool → source node (citation, URL or DOI, passage, date) → claim that cites it (sourced; the passage accounts for its numbers) → review by the fact-checker, who opens the source → report linted so no sentence treats an unreviewed claim as settled → all sourced. Refused on the way: a claim from recall.

optimization — question (objective, constraints) → hypothesis (modelling choice) + experiment (solve configuration) → register_run with objective, feasible, bound or gap, runtime (feasible_bounded) → instrument re-runs the solve → review by the verifier against the constraints → claim "best found, gap x", or "optimal" only with a bound that meets the objective → incumbent feasible. Refused on the way: an objective with no feasibility, "optimal" without a bound.

Each of these is one of the examples, runnable for free.

What you get

• A scheduler that makes no model calls. It issues orders to idle seats from the question board, settles every returned order whose predicates are met, reworks the rest twice, cancels what a fallen premise made moot, and brings in the lead seat only at exceptions and for the report.
• Workers that hold no state. A worker's context is its order and its own turns; every reply from the record tells it whether its order is done. It can be killed: the lease expires and another takes the order, and a run that died can be resumed from the record (run(..., resume=inv)).
• The instrument reproduces; reviewers judge. register_run(code=…) keeps the code; before any review the host's sandbox re-runs it and the record files a lab run — values confirmed, not printed, or contradicted. A reviewer recomputes only a contradiction.
• Claims that can't be flattered. Every claim is checked as it is written (HypGraph's refusal rules and the profile's), the record binds the numbers it already holds, one review settles a question, and the final report is linted against the record before it is accepted.
• A budget that is a rule. Calls and dollars, per run and per order, counted including calls in flight, and shown to every seat.
• Escalation the record decides. A seat may name a deeper model (escalate_to); it is used from the first time the record sends that seat's work back NOT MET — never on the model's own say-so.
• Files the record vouches for. file_tools reads a file only when its bytes match a live artifact; a withdrawn file is refused with the record's reason.
• An audit trail you didn't write. Orders are task nodes, acceptance is a decision, the run files its own provenance: the record is the log, and it verifies by hash.

Seats

Three roles, because they are what the scheduler can check. Jobs are seats: a name, the words it takes, the toolkits it may use, a model and optionally a deeper one to escalate to.

Tools

Tools are named bundles from a registry. hypswarm ships files; anything that executes code or reaches a network is the host's to register, so the swarm never runs what the host did not choose — and a profile that asks for a bundle the host hasn't registered fails loudly rather than running without it.

from hypswarm import toolkits
toolkits.register("python", lambda ctx: [Tool.from_function(my_sandboxed_python)])
result = await run(task, None, model, record="r.hypgraph", folder="work/", toolkits=["files", "python"])

People and other agents as seats

A seat can be external: no model behind it, just a name in the record. The scheduler issues it orders like any other seat and waits; whoever holds that name works the order through the HypGraph MCP server and returns it:

[[seats]]
name = "nicolas"
role = "worker"
external = true

hypgraph --db study.hypgraph --as nicolas mcp     # in Claude Code, Cursor, or any MCP client
# my_work → the order; register_run / add / review → the writes; return_work when the reply says every predicate is met

The record can't tell a person from an agent except by name, and it holds them to the same rules.

Bring your own agent

A seat can be held, in-process, by a whole agent from another framework — your prompts, your tools, your loop — and still be governed by the record: same orders, same refusals, same instrument re-run, same budget.

from hypswarm.bridges.langchain import langchain_agent          # LangChain / LangGraph: any Runnable over {"messages"}
from hypswarm.bridges.pydantic_ai import pydantic_ai_agent       # PydanticAI Agent
from hypswarm.bridges.crewai import crewai_agent                 # CrewAI Crew

seats = [Seat("analyst", "worker", agent=langchain_agent(lambda tools: create_react_agent(llm, tools))),
         Seat("stats", "worker", agent=pydantic_ai_agent(lambda tools: Agent("openai:gpt-4.1-mini", tools=tools))),
         Seat("critic", "reviewer", agent=crewai_agent(lambda tools, order: Crew(...))),
         Seat("lead", "lead")]                                   # a model, e.g. Anthropic(...) or Bedrock(...)

A bridge hands the agent the order, the seat's system prompt and the record's tools in the framework's own tool shape, caps the framework's loop at the calls left in the run, and reports what it used. If the agent doesn't call return_work itself, HypSwarm returns the order with its final answer as the note. Your own framework is one async def agent(order: AgentOrder) -> AgentOutcome away (ADR-009; examples/10-custom-seat-and-toolkit). examples/06-mixed-swarm runs LangChain, PydanticAI, CrewAI, Claude / Bedrock and a person on one record.

One record server, many workers

Workers don't have to share a process. Serve the record, bind writes to tokens, and point the run at it:

hypgraph --db study.hypgraph serve --writable --no-browser --token "$SWARM_TOKEN=harness,quant,risk,lead" --token "$NIC_TOKEN=nicolas"
hypswarm run --task task.toml --profile trading --record-url http://127.0.0.1:8765

In Python, run(..., record=HttpRecord(url, token=...)). A token is bound to the authors it may write as; the harness name is reserved, so an outside seat can hold its own name and nothing else. Every write still goes through the record's checks, the file still verifies by hash, and workers on other processes or machines are stateless.

Providers

The core ships OpenAICompatible (DeepInfra, OpenAI, NVIDIA NIM, vLLM, Ollama, most gateways) and a scripted StubModel for tests. Extras:

Any object with async complete(messages, tools) -> Reply is a model.

Examples

Ten runnable examples in examples/, each free on scripted models and cents on a real provider: one per profile (an eval report, tests the instrument runs, a paper trading desk, a sourced brief, a solve with a bound), the mixed swarm (LangChain + PydanticAI + CrewAI + Claude / Bedrock + a person), a person as reviewer over MCP, a served record with tokens, stop-and-resume with a file withdrawn mid-run, and a custom seat and toolkit from scratch. Several make a deliberately wrong first write so the trace shows the refusal and the honest rewrite.

Installing, today

HypSwarm needs HypGraph's coordination layer, which ships with hypgraph 0.4:

pip install --pre hypswarm                 # pulls hypgraph>=0.4; --pre while it is an alpha

Status

Alpha. Built from the harness the HypGraph harmony study runs agent teams on, and measured there as a preregistered condition before anything is claimed for it. What's built: the scheduler, workers, five profiles with rosters, the tool registry, external seats over MCP, the record server with token-bound writes, resume, escalation, instrument reproduction, verified file tools, the OpenAI-compatible, Anthropic, Bedrock and LangChain adapters, agent seats with bridges for LangChain / LangGraph, PydanticAI and CrewAI, ten runnable examples, and a test suite that runs every scheduler path — and every bridge — on scripted models in seconds. Every design decision is in docs/decisions.

Made by Nicolas Houghtaling at VoodooMods LLC. Apache-2.0.