Search

Open-source agent harness with a ReAct loop, event bus, capability registry, approval gate, and pluggable model/tool adapters.

Local-first AgentOps flight recorder and capability firewall for MCP-based coding agents with OpenTelemetry traces.

🔌 Simplify PostgreSQL interactions with a secure MCP server for LLMs, enabling efficient access to schemas, tables, and query execution.

AI-guided onboarding for human-AI collaboration projects

Define a clear methodology to build, test, and deploy AI agent software with rigorous engineering standards.

🛠️ Structure your AI-assisted development with specialized agents for planning, coding, reviewing, and security in VS Code.

Delegate scoped tasks to worker agents in Antigravity, keeping the main context clear and improving task management efficiency.

Provide a local Swift HTTP server with OpenAI-compatible endpoints that runs tools, returns JSON, and stores files for agent systems.

Agent-neutral handoff and governance protocol for long-running coding-agent work

No description available

Provide ready-to-use AI agent workflows for coding tasks like code review, testing, and dependency audits to streamline developer work.

Lightweight Swift terminal UI library for streaming AI transcripts with in-place updates and tool placeholders.

No description available

opencode plugin: memory bootstrap, idle reflection, skill auto-promotion, and AGENTS.md learning loops via Joplin + pluggable memory backends.

Convert arXiv papers into citation-linked codebases with reproducible notes and implementation files

⚡ Optimize multi-agent orchestration with Agent.cpp, a high-performance C++ inference engine designed solely for Tiny-MoA on CPU.

Provider-neutral autonomous ML research paper writer — ideation -> LaTeX writeup -> peer review -> anti-hallucination numerical audit. Spun out from hermes-sci to remove Hermes-runtime coupling.

🧠 Build a cognitive architecture for AI that mimics human memory, separating episodic and semantic memory while ensuring multilingual support and data integrity.

Monitor LLM app quality in production with Argus AI: scoring groundedness, accuracy, reliability, variance, cost, and safety in 3 lines of code

xcoding by @c7s89r — a local-model coding agent. Claude Code, but powered by Ollama or llama.cpp.