Skip to main content

agent-budget

Hard USD budgets for agents that delegate.

When an orchestrator hands work to several sub-agents at once, each one checks its spending against the same "remaining" figure, none of them sees the others, and together they spend a multiple of what was left. agent-budget fixes that at the delegation boundary: each sub-agent's slice is reserved from the parent before it starts, every amount it books is booked on the parent at the same moment, and the unused part goes back when it finishes.

pip install llm-agent-budget            # no dependencies
pip install "llm-agent-budget[a2a]"     # plus the a2a-python plugins

Child scopes

from agent_budget import Budget

orchestrator = Budget(1.00, name="orchestrator")

with orchestrator.child("researcher", usd=0.60) as research:
    hold = research.reserve(0.06)        # before the model call; refused if it does not fit
    # ... call the model ...
    hold.settle(0.052)                   # what it really cost

    with research.child("fetcher", fraction=0.5) as fetch:   # half of what research has left
        fetch.reserve(0.01).settle(0.01)

print(orchestrator.spent_usd)            # 0.062: every level, as it happens
print(orchestrator.remaining_usd)        # 0.938: the unused slice came back on exit
  • A slice that does not fit raises BudgetExhausted before the sub-agent spends anything.
  • A closed scope (and everything below it) raises ScopeClosed; calls already in flight still settle.
  • kill() stops a scope and its whole subtree. max_depth (default 8) raises DepthExceeded.
  • own_cost_usd + child_cost_usd == spent_usd on every scope.
  • Thread-safe (one lock per tree) and safe in asyncio tasks; current_budget() is the innermost scope entered with with in the current thread or task. One budget can be entered by many threads and tasks at once.

Across agents: A2A, W3C baggage, MCP

BudgetContext is the budget a caller hands down and the cost a callee reports back, in the shape of the A2A budget extension draft (budget{cost, tokens, deadline}, incurred{cost, aggregatedChildCost, tokens, delegations}), plus a reservation{id, amount, currency, expires} for the slice the caller reserved.

from agent_budget import Budget, outbound, to_a2a_metadata, from_a2a_metadata, to_baggage

with Budget(1.00).child("remote", usd=0.30) as slice_:
    ctx = outbound(slice_)
    metadata = to_a2a_metadata(ctx)      # {"https://a2a-protocol.org/extensions/budget/v1": {...}}
    header = to_baggage(ctx)             # "llm.budget.cost.amount=0.3,llm.budget.cost.currency=USD,..."
  • A2A: the whole context under the extension URI in request, message or task metadata.
  • W3C baggage: llm.budget.* members, so anything that already propagates OpenTelemetry baggage carries the budget.
  • MCP: MCP reserves params._meta.baggage for W3C baggage (SEP-414); inject_mcp_meta / extract_mcp_meta put the same members there.

Money is a decimal string on the wire, exact to the nano-dollar. Fields nobody measured are left out, never written as zero.

a2a-python plugins

from a2a import plugins
from agent_budget.a2a_plugin import BudgetClientPlugin, BudgetExecutionPlugin

# Caller: requests made inside a scope carry its budget; replies are booked on it.
plugins.set_global(plugins.sequential(BudgetClientPlugin()))
with orchestrator.child("remote-researcher", usd=0.30):
    async for event in client.send_message(request):
        ...

# Callee: each execution runs inside a Budget of what the caller allowed,
# and every task update reports the cumulative cost back.
handler = DefaultRequestHandlerV2(..., plugins=plugins.sequential(BudgetExecutionPlugin(max_usd=5.00)))
# inside AgentExecutor.execute: current_budget().reserve(...).settle(...)

Strands Agents

from strands import Agent
from agent_budget.strands import Price, SpendCeiling

agent = Agent(tools=[researcher], plugins=[SpendCeiling(usd=0.50, price=Price(input=3.00, output=15.00))])

A Strands plugin (pip install "llm-agent-budget[strands]"): each invocation can spend at most usd, every model call reserves its worst case before it is sent, and an agent used as a tool gets its slice from the caller's budget. See docs/strands.md.

Same format as the Rust crate

llm-budget 0.8 (Rust) has the same scopes and the same contexts. Both test suites read one set of golden fixtures (tests/fixtures/budget_context/), so a Rust orchestrator and a Python agent agree to the last digit.

More: docs/guide.md. Adding it to another project (dependencies, typing, stability, the five-line integration): docs/integrating.md.

MIT license.

Metadata

Release files for llm-agent-budget 0.1.3

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

Source distribution (sdist)

Source distribution for llm-agent-budget 0.1.3
File Size Uploaded Provenance Actions
llm_agent_budget-0.1.3.tar.gz 53.2 kB With provenance Details for llm_agent_budget-0.1.3.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for llm-agent-budget 0.1.3
File Interpreter ABI Platform Actions
llm_agent_budget-0.1.3-py3-none-any.whl Python 3 none any Details for llm_agent_budget-0.1.3-py3-none-any.whl

Total release size: 82.2 kB

Release files / llm_agent_budget-0.1.3.tar.gz

Download URL llm_agent_budget-0.1.3.tar.gz
Size 53.2 kB
Tags Source
SHA-256 checksum
How to use checksums
1db517ea198327b3a08243ff78d521fc7fb2827309c5586e2c684c217360e837
BLAKE2b-256 checksum
How to use checksums
530087d590bf45ef841de32da9a39406b5c15d0095cadd7dac438e8fe63b558a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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 Nov 18, 2026.

Transparency log

Release files / llm_agent_budget-0.1.3-py3-none-any.whl

Download URL llm_agent_budget-0.1.3-py3-none-any.whl
Size 29.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
37ab5beba3dc2263198c1b1ad2f1522b8d011da48f37c33f7b4bd28f3591e2ee
BLAKE2b-256 checksum
How to use checksums
3b025fd756acdd3c5e6e62700424f4a47a228541eed623f05b297eccc29a0e45
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

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 Nov 18, 2026.

Transparency log

Security for llm-agent-budget 0.1.3

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

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for llm_agent_budget-0.1.3.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 Nov 18, 2026.

Transparency log

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

0.1.3 This release

2 release files Full provenance

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