Adam: An Embeddable Cross-Platform AI Agent Library in C

Adam is an embeddable AI agent library written in C. It offers a full agent loop — tool calling, memory, sessions, voice, streaming, structured output — as a single #include. It supports cloud APIs (Anthropic, OpenAI, Google Gemini, Groq, Together, xAI) and local models via llama.cpp through the same interface. Compiles on macOS, Linux, Windows, iOS, Android, and WASM.

Quick Start

#include "adam.h"

int main(void) {
    adam_init();
    adam_settings_t *s = adam_create_settings();
    adam_settings_set_provider(s, ADAM_API_ANTHROPIC, getenv("ANTHROPIC_API_KEY"), "claude-sonnet-4-20250514");
    adam_history_t *h = adam_history_create();
    adam_run_result_t r = adam_run(s, h, "What is the capital of France?");
    printf("%s\n", r.final_response); // "The capital of France is Paris."
    adam_run_result_free(&r);
    adam_history_destroy(h);
    adam_settings_destroy(s);
    adam_cleanup();
}

make deps     # build llama.cpp + whisper.cpp
make all      # build libadam.a
make test     # run 161 tests (ASan + UBSan)

Key Features

• Agent loop – tool calling with automatic iteration until final response
• Three providers – Anthropic, OpenAI, Google Gemini + any compatible API + local GGUF via llama.cpp
• Local vision – multimodal image understanding via llama.cpp + mmproj (Gemma 3, LLaVA, etc.)
• Image generation – native image output via Gemini image models
• Database extensions – SQLite and PostgreSQL extensions that embed Adam as SQL functions
• 13 built-in tools – file I/O, shell, calculator, SQL, web fetch/search, HTTP POST, memory, research, multi-agent
• Long-term memory – hybrid BM25 + vector search via SQLite (sqlite-memory + sqlite-vector)
• Session persistence – save/load conversations with UUIDv7 keys
• Telegram bot – full-featured with text, voice, images, tools, and memory
• Voice – STT (Whisper cloud/local) + TTS (cloud/system) + full audio pipeline
• Streaming – real-time token delivery via callback
• Structured output – adam_run_json() with validation and retry
• Evolution loop – self-improving agent: iterate, score, refine strategy
• Research mode – autonomous multi-iteration info gathering with report synthesis
• Multi-agent – Agent A invokes Agent B as a tool, with independent settings/tools
• Guardrails – pre-send and post-receive validation callbacks
• Response cache – LRU hash table keyed on model + message history
• History management – clone, summarize (LLM-based compression), token estimation
• Thread pool – concurrent agent execution with job queue
• Filesystem sandbox – tools restricted to explicitly allowed directories
• Arena allocator – zero-leak per-iteration memory with automatic cleanup

Build Targets

make deps     # Build llama.cpp, whisper.cpp (+ mbedtls/curl on Linux)
make all      # Build libadam.a
make test     # Build & run unit tests (ASan + UBSan)
make chat     # Interactive text chat (cloud API)
make chat GGUF=models/model.gguf   # Interactive text chat (local)
make vision GGUF=models/model.gguf MMPROJ=models/mmproj.gguf  # Local vision test
make talk     # Voice agent (cloud)
make talk LOCAL=1  # Voice agent (fully local)
make memory   # Memory system tests
make clean    # Remove all build artifacts

Full API documentation is available in API.md with every function, type, and callback.