tessera-crewai 0.1.0

Drop-in Tessera integration for CrewAI. One line of config routes your CrewAI agents' LLM calls through Tessera's auto-route + auto-cache + auto-compress + auto-batch proxy. Free 60M tokens/mo. Production: 20% of measured savings.

tessera-crewai

Drop-in Tessera integration for CrewAI. One line of config routes every LLM call your crew makes through Tessera's auto-route + auto-cache + auto-compress + auto-batch proxy.

Free 60M tokens/month. Production: 20% of measured savings. No card up front.

Install

pip install tessera-crewai

Requires Python 3.10+. CrewAI is a peer dependency — install it in your environment alongside this package.

Usage

The most common pattern uses one of the bundled factory functions to construct a pre-wired CrewAI LLM instance:

from crewai import Agent, Crew, Task
from tessera_crewai import tessera_openai_llm

llm = tessera_openai_llm(
    model="gpt-4o",
    openai_api_key="sk-...",   # your OpenAI key
    tessera_api_key="tsr_...",  # get a free one at tesseraai.io/dev
)

researcher = Agent(
    role="Senior Researcher",
    goal="Uncover cutting-edge developments in AI",
    backstory="You are a seasoned researcher...",
    llm=llm,
)

# Rest of your CrewAI code runs unchanged — Crew, Task, kickoff()
# all route through Tessera and benefit from auto-optimization.

For Anthropic models:

from tessera_crewai import tessera_anthropic_llm

llm = tessera_anthropic_llm(
    model="claude-sonnet-4-6",
    anthropic_api_key="sk-ant-...",
    tessera_api_key="tsr_...",
)

For explicit LLM construction (rare — useful when you need fine-grained LLM kwargs):

from crewai import LLM
from tessera_crewai import tessera_openai_config

llm = LLM(
    model="openai/gpt-4o",
    api_key="sk-...",
    **tessera_openai_config(api_key="tsr_..."),
)

What Tessera does for your CrewAI workloads

• Auto-route — calls to expensive models are evaluated for a cheaper alternative that preserves quality on canary samples.
• Auto-cache — exact-match + semantic cache for repeat queries. CrewAI's tool-use loops often hit identical sub-prompts; cache returns are free.
• Auto-compress — system prompts and verbose tool descriptions compressed losslessly before they hit the upstream provider.
• Auto-batch — async crews with batch-tolerant SLAs get arbitraged onto provider batch APIs for ~50% cost reduction.

All gated by per-workload quality canaries; toggle any mechanic on/off from the Tessera dashboard. Free Sandbox tier gives you observe-only mechanics; Production tier unlocks the full stack.

Supported providers (v0.1)

Provider	Status	Config function
OpenAI	✅ verified	tessera_openai_config, tessera_openai_llm
Anthropic	✅ verified	tessera_anthropic_config, tessera_anthropic_llm
Mistral / Groq / Cohere	🚧 queued for v0.2	—

v0.1 covers ~85% of customer traffic per our outreach research. Open an issue if you need a provider on the queue surfaced sooner.

Companion packages

Companion to tessera-sdk (vanilla provider SDKs), tessera-langchain (LangChain integration), tessera-vercel-ai (Vercel AI SDK integration), tessera-llamaindex (LlamaIndex integration), tessera-mastra (Mastra Agent framework integration), tessera-pydantic-ai (Pydantic AI integration), and tessera-autogen (AutoGen 0.4+ multi-agent integration). Same proxy, same mechanic stack, CrewAI-shaped API.

License

Apache 2.0 — see LICENSE.