Open-source agent memory framework that retains experiences, recalls relevant information, and learns over time. Includes a server, client SDKs and APIs for building applications with persistent memory.
Fireworks AI listing for Z.ai’s GLM 5.3 Flash, a 320B-parameter mixture-of-experts model with a 1M-token context window. Supports serverless inference, function calling, image input and LoRA training; standard serverless pricing is listed.
Hermes documentation for Qmd, a local hybrid search engine for notes, documents, and transcripts. Covers installation, collection indexing, keyword and semantic search, and MCP integration.
An Apache Incubator local-first workspace for AI agents. It records model messages, tool calls, permission decisions, and termination events in an append-only log for auditable agent runs.
A local command-line search engine for documents, knowledge bases, and meeting notes. It indexes personal content locally and supports current retrieval approaches.
A non-coder compares a Claude CoWork setup with ChatGPT Work after importing skills and workflows. It covers subscription and model trade-offs, project and knowledge-management workflows, desktop voice, plugins versus GPTs, shared-memory experiments, and the importance of human review.
A benchmark comparing eight AI agent harnesses running the same Kimi K3 model across 25 business-application tasks. It compares pass rates, speed, tool calls, token usage, and estimated cost, finding substantial differences between harnesses.
A controlled benchmark comparing eight agent harnesses—Oh My Pi, Kimi Code, Hermes Agent, Claude Code, Pi Agent, OpenCode, Grok Build, and Codex—using the same Kimi K3 model via OpenRouter, identical tools, and 25 complex business-app tasks. Results show a 20-point pass-rate spread, major differences in speed and cost, and that more tool calls did not guarantee better outcomes.
Self-hosted AI gateway routing across 268 providers with auto-fallback, token compression (RTK+Caveman), built-in MCP server, and cloud agent support. 33k+ stars, MIT license.
Self-hosted AI router with 3-tier auto-fallback (subscription → cheap → free) across 60+ providers. RTK+Caveman token compression saves 20-65%. One OpenAI-compatible endpoint for all CLI tools. MIT license.