lechmazur / pactLinks
A benchmark for conversational bargaining by language models. In each 20‑round match one LLM plays buyer, one plays seller, and both hold a hidden private value. Every round they swap a short public message, then post a bid or ask; a deal clears whenever the bid meets the ask.
☆31Updated 5 months ago
Alternatives and similar repositories for pact
Users that are interested in pact are comparing it to the libraries listed below
Sorting:
- ☆37Updated 5 months ago
- Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs☆24Updated 6 months ago
- Tensor-Slayer : Manipulate weights and tensors of LLMs to achieve performance upgrades and introduce a novel inferenceless mechanistic in…☆27Updated 8 months ago
- Chat strategies for LLMs☆128Updated 2 weeks ago
- Pivotal Token Search☆144Updated last month
- ☆20Updated 3 months ago
- ☆107Updated 2 months ago
- powerful and fast tool calling agents☆80Updated 10 months ago
- ~ streaming agents☆75Updated last month
- ☆100Updated 8 months ago
- Tools for LLM agents.☆61Updated last year
- ☆85Updated 4 months ago
- Explore the answer-space of open LLMs☆184Updated last week
- Automated LLM Coding Tournaments. There can be only one (winning code solution from the competing AIs)☆45Updated last week
- synthetic dataset generation workflow using local file resources for finetuning llms.☆82Updated 3 months ago
- Offline-first, desktop AI assistant tailored for educators, enabling them to generate questions directly from source materials.☆23Updated 5 months ago
- A mcp server that uses the Osmosis-Apply-1.7B model to apply code merges☆53Updated 6 months ago
- Code for WALT – Web Agents that Learn Tools☆63Updated 2 months ago
- The engine powering hundreds of thousands of MCP connections 🤖 🔥☆197Updated this week
- Real-world AI engineering dataset creation, SFT fine-tuning, and GRPO alignment ETL pipeline.☆32Updated 5 months ago
- ☆20Updated 11 months ago
- Dialectical reasoning architecture for LLMs (Thesis → Antithesis → Synthesis)☆107Updated last week
- Agentkube - Run Kubernetes Like Never Before☆24Updated last month
- 🎲 codenames, but AI plays against AI. (OpenAI o1)☆50Updated last month
- ollama like cli tool for MLX models on huggingface (pull, rm, list, show, serve etc.)☆126Updated this week
- Train an adapter for any embedding model in under a minute☆130Updated 9 months ago
- Install custom Factory Droid subagents and delegate work using custom slash commands.☆80Updated 3 months ago
- ☆50Updated last month
- a Python library that uses Reinforcement Learning (RL) to train LLMs.☆42Updated 5 months ago
- AgentX python SDK. Build multi-agent AI workforce.☆44Updated 7 months ago