A minimal coding-agent harness built to measure what context management actually costs: constraint survival after compaction (8%→83%), default-FAIL verification against false completions, and KV-cache prefix design (21%→90%). Stdlib-only, real deepseek-chat runs
GitHub repository with 41 stars and 8 forks.
Language: Python
Topics: ablation-study, agent-harness, context-engineering, context-management, deepseek, evaluation, kv-cache, llm, llm-agents, prompt-caching
Trending score 0.07, freshness score 0.36, stars gained +0, forks gained +0.
2026-11-02: 41 stars and 8 forks.
Debloat any Android or Google TV over Wi-Fi and get an Apple TV-style home.
GitHub repository with 50,021 stars and 6,296 forks.
Trending score: 6.66; stars gained: +2,449; forks gained: +403.
Language: Python
Topics: adb, adblock, android-tv, android-tv-launcher, apple-tv, bloatware-removal
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
GitHub repository with 98,705 stars and 10,947 forks.
Trending score: 6.48; stars gained: +2,186; forks gained: +270.
Language: Python
Topics: ai, audiobook, cuda, dubbing, elevenlabs-alternative, huggingface
DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.
GitHub repository with 54,169 stars and 6,628 forks.
Trending score: 6.35; stars gained: +1,917; forks gained: +225.
Language: Python
Topics: ai-agents, ai-tutor, clawbot, cli-tool, deepresearch, interactive-learning
Open-source skills for designing and reviewing software with AI agents
GitHub repository with 10,275 stars and 682 forks.
Trending score: 6.27; stars gained: +2,304; forks gained: +157.
Language: Python
Topics: agent-skills, ai-agents, antigravity, claude-code, claude-code-plugin, claude-skills
Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less than 120 seconds.
GitHub repository with 43,005 stars and 1,779 forks.
Trending score: 6.15; stars gained: +3,355; forks gained: +26.
Language: Python
Topics: agent-evaluation, ai, ai-alignment, ai-evaluation, ai-governance, ai-safety
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
GitHub repository with 140,936 stars and 13,472 forks.
Trending score: 5.87; stars gained: +1,066; forks gained: +123.
Language: Python
Topics: ai-agents, antigravity, ast, claude-code, code-analysis, code-search