#llm

Pest Browser Evals

Watch, approve and steer your coding agents from your phone.

Self-hosted AI knowledge agent — TypeScript, Bun, MCP. Own your data, run your own brain.

Local bridge for using OpenAI-compatible LLM providers with Codex and Claude coding clients.

🧠 An adaptation of the MCP Sequential Thinking Server to guide tool usage. This server provides recommendations for which MCP tools would be most effective at each stage.

Local context-compression layer for agent tool outputs. Claude Code PostToolUse hook or generic filter, single Go binary.

AI development assistant CLI for Symfony projects

Code search that lets AI coding agents find the right files in fewer steps. Use the hosted endpoint or self-host, works with Claude Code, Copilot and Cursor via MCP.

LLM-driven browser automation with wallet extension testing. Accessibility tree + optional vision.

Open source coding agent forked from OpenCode.

Deterministic execution harness for AI agents — goals in, structured tasks out, verified results back.

A type-safe-by-design, cost-limited virtual machine that enables the safe execution of untrusted code anywhere

C# SDK for the OpenRouter API -- LLM gateway with 500+ models, model discovery, routing, and generation stats

saige - Super Artificial Intelligence Graph Environment. A unified Go SDK, CLI, and MCP server for streaming AI agents, knowledge graphs, and RAG pipelines, with Ollama, OpenAI, Anthropic, and Google providers behind one interface.

TurboQuant+ KV cache compression for vLLM. 3.8x smaller KV cache, same conversation quality. Fused CUDA kernels with automatic PyTorch fallback.

Compact PHP repository symbol maps for coding-agent navigation.

Working-memory layer for coding agents: per-task session plans, decisions, assumptions, checkpoints, claim metadata, and retention.

✨多agent实现全自动AI小说生成

Agentic terminal AI assistant with a Bubble Tea TUI, code-graph review, semantic search, multi-provider LLMs, and MCP tools.

🌿 Production-grade Go framework for conversational AI agents — LLM abstraction, RAG, memory, WhatsApp, scheduling & observability built in.

OwlCoda — local-first foundation for governed AI business execution: evidence, replaceable executors, admitted results, and explicit authority boundaries.

MCP server for Kling AI video generation via AceDataCloud API

MCP server for Luma AI video generation via Ace Data Cloud.

MCP server for Google SERP search, images, news, maps, and knowledge graph results.

The core of FrontierHarness

Pi client/server fork for proxy-safe incremental requests

Multi-account tool broker for AI agents — use tools on demand from the CLI or connect through MCP, with credentials kept local.

Runtime constitutional governance for autonomous AI agents: six gates, 12 hard constraints, and cross-session risk composition — escalates on the trajectory, catching agents that pass every individual gate but accumulate risk across a sequence. pip install constitutional-agent

Self-hosted agentic OS — a Vibe-Engineering platform for Builders. Connect Claude Code, Codex or Hermes Agent to Discord, Telegram, WhatsApp, Slack & Email. EU AI Act 2026 & GDPR compliance by architecture.

The self-correcting memory layer for AI agents. Zero-dependency Python memory and MCP server. Supersede, revert, or forget a value deterministically. Verifiable erasure, witness-backed tamper-evident receipts, EU AI Act ready.