abstractcore.ai valid

AbstractCore

Unified Python interface for cloud + local LLM providers with streaming, tool calling, structured output, media handling (images/audio/video + documents), embeddings, and an optional OpenAI-compatible HTTP server. Default install stays lightweight; features are enabled via extras.

For agents: Python library giving one interface to cloud and local LLMs, with streaming, tool calling, structured output, embeddings and an optional OpenAI-compatible serve

python llm libraryllm providerstool callingstructured outputopenai-compatible serverembeddings

Their llms.txt

The beginning of the file, from our validated copy saved 2026-10-23T15:27:27.765Z. Cached copy · Source on abstractcore.ai

# AbstractCore

> Unified Python interface for cloud + local LLM providers with streaming, tool calling, structured output, media handling (images/audio/video + documents), embeddings, and an optional OpenAI-compatible HTTP server. Default install stays lightweight; features are enabled via extras.

Last reviewed against source: 2026-05-04. Package version in source: 2.13.2. Supported Python: 3.9+; GitHub CI tests 3.9, 3.10, 3.11, 3.12, and 3.13.

This is the curated, high-signal index for agents. For a self-contained handbook with the important details inlined, read `llms-full.txt`.

Important notes:
- Default tool execution is **pass-through**: AbstractCore returns tool calls; your host/runtime executes them.
- AbstractCore is **offline-first** for local models: it will not silently download model weights (download/pull explicitly).

Ecosystem note:
- AbstractCore is part of **AbstractFramework** (umbrella: https://github.com/lpalbou/AbstractFramework).
- In the ecosystem, **AbstractRuntime** is the recommended runtime for executing `response.tool_calls` durably (policy, retries, persistence): https://github.com/lpalbou/abstractruntime

Quick start:
- Install: `pip install abstractcore`
- Hosted SDK bundle: `pip install "abstractcore[remote]"` (OpenAI + Anthropic SDKs; OpenRouter/Portkey/local `/v1` providers use core HTTP dependencies)
- First steps: `docs/getting-started.md` -> `docs/prerequisites.md`
- Run the gateway server: `pip install "abstractcore[server]"` then `python -m abstractcore.server.app`
- Run the single-model endpoint: `pip install "abstractcore[server]"` then `abstractcore-endpoint --help` (see `docs/endpoint.md`)
- Repo/dev checks: `pip install -e ".[dev,test]"` ; `pytest -q` ; `black .` ; `ruff check .`

## Read First

- [README](README.md): what AbstractCore is + install matrix
- [Docs index](docs/README.md): recommended reading paths
- [Getting Started](docs/getting-started.md): `create_llm(...)`, `generate(...)`, streaming, tools, structured output, media
- [Prerequisites](docs/prerequisites.md): provider setup (keys/base URLs) + local hardware notes
- [FAQ](docs/faq.md): common issues + setup gotchas

## Examples

- [Examples index](examples/README.md): organized by topic + a guided learning path
- [Learning path](examples/learning_path/README.md): 6 scripts in order (`01_...` → `06_...`)
- [Prompt caching](examples/prompt_caching/README.md): `CachedSession` + attachments + REPL demo
- [Media](examples/media/README.md): inspect pipeline + image/video/audio demos
- [Tools](examples/tools/README.md): tool calling + host execution (ToolRegistry vs manual dispatcher)

## Core API + Concepts

- [API (Python)](docs/api.md): public API map and common patterns
- [API Reference](docs/api-reference.md): full function/class listing
- [Generation parameters](docs/generation-parameters.md): max tokens / thinking / temperature semantics across providers
- [Prompt caching](docs/prompt-caching.md): `CachedSession`, cache keys, and fil
…

Related sites

Find similar publishers by meaning →

Other listed sites in AI and machine learning. See the whole category →

Machine-readable: GET /v1/resolve?q=abstractcore.ai · GET /v1/domain/abstractcore.ai · this page as Accept: application/json or text/markdown · MCP lookup_domain

Automatically discovered from public files. Inclusion does not imply endorsement or publisher participation.

Claim my listing on Agent Web Map for abstractcore.ai:
1. POST https://agentwebmap.com/v1/sites/abstractcore.ai/claims and keep claim_id and claim_secret private.
2. Publish the proof: add the line "AgentWebMap ownership: <token>" (token from step 1) to https://abstractcore.ai/llms.txt, or use the DNS, meta-tag or well-known method the response describes.
3. POST https://agentwebmap.com/v1/sites/abstractcore.ai/verify with {"claim_id": "...", "claim_secret": "..."}.
4. Save the api_key from the answer; it manages the listing (PATCH https://agentwebmap.com/v1/sites/abstractcore.ai).
MCP equivalent: tools begin_ownership_claim, then verify_domain, at https://agentwebmap.com/mcp. Docs: https://agentwebmap.com/docs#verify

Corrections or removal requests: contact the directory.