#llm

Persistent, queryable memory for AI agents with semantic recall, layered storage, snapshots, and multi-agent scoping

Sandboxed JSON-over-stdin/stdout tool executor for AI coding agents with 19 tools, workspace confinement, and guarded mutation.

Agentic AI development loop that splits Design, Code, Review, and Test into isolated roles with deterministic guardrails

Small MIT-licensed runtime for bounded LLM traversal, inspired by FPF and focused on practical agent behavior.

No repository description published.

Agoria: an agent-to-agent coordination hub. Named channels, per-channel shared state, an attention/obligation model, a verifiable transcript, message-driven triggering, and a git-friendly markdown mirror. Framework-agnostic (MCP + CLI + Python).

Go agent knowledge library for CLIs — embedded guides, schema introspection, and skill export

No repository description published.

Turn Codex into a full-scale ACP server. Zero deps. No OpenAI API keys. Uses your existing Codex subscription.

ACP-backed Google ADK agent adapter for Go

Reusable Go runtime packages for building and configuring ACP-backed agents

Docusaurus plugin for generating LLM-friendly documentation following the llmstxt.org standard

Transparent logging proxy for Claude Code — audit what eats your context, with local ClickHouse/Loki/Grafana analytics

Universal AI router — save 20-40% tokens with RTK and never stop coding. Connect Claude Code, Cursor, Antigravity, Kiro, Copilot, Codex, Cline & any OpenAI-compatible client to 40+ providers & 100+ models via one local endpoint. Zenith sub-1ms failover, MITM, multi-account.

A Go SDK for the Claude Code CLI: one-shot runs, interactive sessions, in-process Go tools, permission & hook callbacks, inline subagents. Behaviorally verified against the real binary.

A superfast proxy and smart load-balancer for AI Inference — virtualize models, share local and provider back-ends, optimal caching, lock-in sampling parameters, debug message flow and obtain OTel metrics

Extension for the pi coding agent that intelligently routes each turn to the right LLM tier (high/medium/low) based on task intent, session budget, context size, and custom rules.

Strip common prompt injection surfaces.

Scriptable, multi-provider AI agent for the terminal — pipe into it, script it, run it on any model, cloud or local

Search engine

ローカルLLM（mlx / mlx-vlm / llama.cpp / router）を OpenAI 互換 API として起動・管理する軽量サーバー

Unofficial MCP server for Twine

Jurisdiction-aware judicial reasoning platform — a model-agnostic AI engine that produces citation-backed, adversarially-tested draft case analyses for human sign-off. Non-binding by design.

High-performance, multi-provider LLM SDK for Go. Unified access to OpenAI, Anthropic, Gemini, Ollama, OpenRouter with adaptive rate limiting and concurrency control.

Local agent-to-agent artifact exchange for LLM workflows via HTTP, CLI, and MCP.

Makes AI stateful across sessions. Workflow: chat → idea → design → reqs → plan → do_step(s) → done, with fresh scoped context, staleness detection, and human approval at every phase. Roadmap & history of shipped features.

No repository description published.

Tako CLI — AI coding tools launcher

Build programmatic SEO pages that stay consistent.

MCP server with 30 tools for block chain data and ops— setup, token lookups, wallet balances, live chain queries using micro payment on x402.