finkritq as framework-neutral tool contracts and capabilities for any agent framework.
Project description
finkritintel
The bridge layer of the finkrit stack. It exposes finkritq (the deterministic quant core) as framework-neutral tool contracts an agent can call, without depending on any particular LLM framework.
Deliberately pydantic-free and agent-framework agnostic, so you can wire these tools into pydantic-ai, LangChain, an MCP server, or your own runtime. finkrit's own agent layer (finagent) is just one consumer.
Install
pip install finkritintel # pulls finkritq
What it gives you
- ToolContract — agent-facing metadata for a tool (name, description, tags), independent of how it is implemented.
- ToolBinding — a contract paired with an input and output schema and a
concrete finkritq implementation.
binding.execute(...)runs it. - Capability — a named group of bindings (risk, performance, optimization) an agent exposes as one unit.
The integration.finkritq subpackage wires finkritq functions into ready-made
bindings, with room for other data sources later.
Example
List the tools a capability offers, framework and LLM free:
from finkritintel.capability.risk import RISK_CAPABILITY
for binding in RISK_CAPABILITY.tools:
print(binding.contract.name, "-", binding.contract.description)
Each binding carries the schema and the callable, so a framework author can turn it into a tool however that framework expects.
License
Apache-2.0. See LICENSE.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file finkritintel-0.1.0.tar.gz.
File metadata
- Download URL: finkritintel-0.1.0.tar.gz
- Upload date:
- Size: 24.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.11.2 {"installer":{"name":"uv","version":"0.11.2","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
0bc68edc9258773357c32071cbcfe0f03e8bda01ce9b247dbdbbaa05b11a1e27
|
|
| MD5 |
c8c55ba596a7ce37509a6b886de8e9ff
|
|
| BLAKE2b-256 |
4ed8c7c28b056c72f374652d03e0763604fae756eac5e21c7b39a4cf63352a2f
|
File details
Details for the file finkritintel-0.1.0-py3-none-any.whl.
File metadata
- Download URL: finkritintel-0.1.0-py3-none-any.whl
- Upload date:
- Size: 28.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.11.2 {"installer":{"name":"uv","version":"0.11.2","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
46fed79b62859eb59b69b3a4098e7aa8a5d27ab28b6f9c0eacef477edd79f0ef
|
|
| MD5 |
82cdd23e4a3139756ff2ea8ecee90de1
|
|
| BLAKE2b-256 |
1ef55d754267dfc7013c10759843ac2ce9eb4ceaf3f0fdb102e99bfdf1b5cb06
|