#llm

Across 348 long-horizon benchmark sessions, Tura used up to 83.1% fewer turns on the rewrite benchmark and improved the DeepSWE pass rate by up to 16.7 percentage points compared with Codex CLI.

A Go-native framework for LLM agents, with OpenTelemetry observability built in.

Small polyglot cost ledger for LLM and agent API calls

Опис репозиторію не опубліковано.

Automate Ghidra reverse engineering from the command line — headless analysis, decompilation, and structured JSON output for AI agents like Claude Code

Standalone DAG workflow engine for Go — 15 step types, MCP integration, durable Postgres execution (SKIP LOCKED), templates, approvals, crash recovery

Agent control plane for governed AI coding: validate changes, enforce policy gates, track findings, proofs, and evals based on your habits.

AI-native TypeScript 3D SDK for browser 3D apps, prompt-to-code scenes, GLB/glTF product viewers, WebGL/WebGPU, Vite templates, diagnostics, and deploy checks.

Backthread keeps the thread on what your AI coding agent ships — it captures the why behind every change and turns it into a living 'How it works' view of your codebase you can actually query.

Just as a prism separates light into distinct colors, this delegation layer separates complex workflows into focused, single-purpose local agents.

Cisco AI Defense middleware for LangChain agents

A Rust agent SDK, harness, and coding agent — safe by construction (non-bypassable authorization → approval → guarded IO).

Zero-config NL-to-SQL data engine with multi-tenant isolation, built for embedding in multi-tenant SaaS apps.

Host + AG-UI bridge for LangGraph agents — agent-spec loading, layered config, and typed in-process streaming

Evi — local-first personal AI assistant (CLI + web + desktop) over local LLM backends

影视资源分享文本的结构化采集、解析与网盘链接校验 - 采集/抽取/校验分层幂等，可单独重跑

The finmap.org MCP server provides comprehensive historical data from the US, UK, Russian and Turkish stock exchanges. Access sectors, tickers, company profiles, market cap, volume, value, and trade counts, as well as treemap and histogram visualizations

Local-first BYOK AI workspace for reusable assistants, prompts, tools, skills, model choices, and private local history across multiple LLM providers.

Keep docs and AI-agent instructions in sync. Scaffold docs-as-code, generate agent files, and fail CI when docs drift.

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

Sandbox runtime for AI coding agents. Firecracker microVMs, a single Go binary, snapshot/fork as first-class primitives.

Опис репозиторію не опубліковано.

Free, local-only TUI for capturing OTEL telemetry from Claude Code and OpenCode into a local SQLite database — cost, tokens, tool usage, and latency analytics.

Policy-aware model execution with portable routing, budgets, fallbacks, and receipts

The open standard AI gateway — PII protection, audit, reliability & cost control as composable interceptors. Same API in Python, Java & JavaScript.

Rust interfaces to the streaming code protocols.

verification toolchain for TypeScript (Tech Preview)

A minimalist, LLM-powered AI translation & dictionary CLI tool for developers.

Agent Tool Protocol

Evidence-first, multilingual, S3-native RAG — answers only from cited evidence (exact quote, page, bbox) and abstains when the evidence is weak, missing or conflicting. The guarantee is "no ungrounded claim". Byte-identical core across Python, Go and JavaScript. Docs: https://muthuishere.github.io/citenexus/