AI/ML●●Solid
LLM-wiki LLM-compiled knowledge bases with multi-agent research v0.0.20
Multi-agent research with fuzzy routing and cross-wiki synthesis.
Big BrainNiche Gem
nvk
202mo ago
Back to browse
GitHub Repository
An embeddable cross-platform AI agent library written in C. Cloud and local LLMs, tool calling, long-term memory, voice, sessions, research mode, self-evolving loops. The SQLite of agent frameworks: small, portable, just works.
94 starsC
Adam – An embeddable cross-platform AI agent library
by marcobambini·May 6, 2026·24 points·9 comments
AI Analysis
●●●BangerWizardryBig BrainNiche Gem
Agent framework in a single C header file that actually runs local models offline.
Strengths
- •Wire-protocol parsing for SQLite/Postgres extensions means zero IPC overhead.
- •Hybrid BM25 + vector search memory runs entirely inside the host process.
- •Self-evolving loops and multi-agent recursion implemented in pure C.
Weaknesses
- •C API requires manual memory management, steep learning curve for Python devs.
- •No Windows binaries provided yet, users must compile from source.
Category
Target Audience
C/C++ developers, embedded systems engineers, privacy-focused AI builders
Similar To
LangChain · LlamaIndex · Semantic Kernel
Similar Projects
Security●●●●Gem
Edictum – Runtime governance for LLM agent tool calls
Proves text safety ≠ tool-call safety; catches hidden harmful executions deterministically.
Zero to OneBig BrainWizardry
acartag7
203mo ago
AI/ML●●●Banger
FERNme – agent memory that updates with ~zero LLM calls
Zero-LLM writes with Hebbian learning cuts token costs 77× versus extraction memory.
Big BrainWizardry
mirkofr
301d ago
AI/ML●Mid
The Agent Skills Standard – A modular approach to LLM context
Modular context folders beat monolithic prompts for scaling AI agent instructions.
Big Brain
muhammad-shafat
303mo ago
AI/ML●●●Banger
Castor – a secure execution layer for LLM agents
Kernel interception stops runaway agents where LangGraph and AutoGen only advise.
Big BrainSolve My ProblemShip It
claytonia
102mo ago
Security●●Solid
VoiceGoat – A vulnerable voice agent for practicing LLM attacks
CTF-style flags for voice prompt injection make learning LLM security actually fun.
Niche GemRabbit Hole
xmhatx
1411mo ago