Autonomous AI agents that perform tasks independently
Chinmay Kakatkar
agent-tco: Pareto-optimal configuration of agentic workflows.
inis.run
inis.run sandbox provider for Strands Agents
wane528
Turn failed agent traces (wrong tool, bad args, wrong format, over-refusal) into clean tool-call/behavior-fix SFT/DPO training data
...moreinis.run
Pydantic AI toolset for inis.run sandboxes
Topicspot
Check whether your agent instruction files reach the agent at all: Codex, Claude Code, Cursor, Copilot.
oleg494
Local developer MCP server with Streamable HTTP, OAuth 2.1, filesystem tools, commands and Git repository context.
ZenHG
22-agent Mixture-of-Agents pipeline with LongLoop for 24h autonomous iteration: smart routing sends easy tasks to Flash, hard tasks to flagships, cutting token costs ~90%. One-command deploy（一键部署，22 个 agent 的 MoA 流水线，长程循环可自主迭代 24 小时，智能路由省约 90% token 成本）
...morePranesh
A local-first agentic coding harness: streaming tool loop, permission gating, context compaction, subagents, and any LLM provider.
...moreTask-driven context compression for LLM agents with analytical compression strategy
kaspernj
Stream Codex, Claude, Kimi Code, and OpenCode worker progress to an explicit Telegram destination
luckyv
Self-observing AI agent SDK: OpenTelemetry instrumentation for AI SDK agents plus an LLM-over-traces behavioral drift detector. Bring your own model client — no provider SDKs bundled.
...morePerseus Computing LLC <[email protected]>
Perseus Vault persistent, local, encrypted memory for Pydantic AI agents — exposed as a Toolset.
ProjectSupervisor contributors
Project-neutral autonomous multi-agent supervision control plane
pusucip25
🔌 Portable uncensored AI agent that runs from USB/SSD. 13 autonomous tools (deep search, OSINT, code execution), persistent memory, 5 GGUF models, zero install, zero traces. Cross-platform (Windows + Linux).
...moreshanananana
AI Agent platform for incident triage & project Q&A on OpenHands — Git sync, logs, config center, Ingress/Webhook
victorche
Lighthouse for your coding agent — scans local Claude Code session history for recurring failures.
raghavendrashivam474
Offline-first agentic AI framework with planning, tool orchestration, memory, and local LLM support built using FastAPI and Ollama.
...moreyuexuanchi-sys
完整的 Godot 4.6 卡牌 RPG：包含回合制卡牌战斗、牌组与状态系统、仪式锻造、城市探索、NPC/委托/情报和小游戏、高塔生成与推进、可离线降级的 AI GM 叙事、运行时美术与 7 首 BGM；另含可独立测试的 TypeScript/WebSocket 权威服务端原型、Godot/Vitest/WebQA 测试和跨平台导出配置。
...moreJimmi Carroll
Agent memory gated on surprise, budgeted on attention, with provenance and validity intervals.
Open host agent for the FlashML fragmented-compute network: join, benchmark, execute sandboxed ML tasks, earn contribution credits.
...moreAgentWeb contributors
Turn websites into fast, structured commands for coding agents
TestNeo
TestNeo Agent SDK — emit agent_run_summary.v1 and ingest into TestNeo (framework adapters optional).
Marcelo Adan
AI Agent Toolkit - CLI unificada para herramientas de desarrollo impulsadas por IA
zceeeeee
MCP Server framework that lets AI Agents write Python scripts to control browsers via Playwright. Features skill routing, self-healing selectors, and experience accumulation.
...more