This is the repo for the paper A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression
☆48Apr 23, 2026Updated 6 months ago
Alternatives and similar repositories for TACO
Users that are interested in TACO are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆42Jul 15, 2025Updated last year
- Accelerating the development of large multimodal models (LMMs) with lmms-eval☆14Oct 14, 2024Updated 2 years ago
- ☆105Dec 6, 2024Updated last year
- ☆13Sep 10, 2025Updated last year
- ☆21Sep 21, 2026Updated last month
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- This is the official implementation for AgentSPEX: An Agent SPecification and EXecution Language☆103Jul 22, 2026Updated 3 months ago
- 防沉迷提醒APP代码☆18Nov 1, 2026Updated last week
- [ACL 2026] Official repo for "Native Hybrid Attention for Efficient Sequence Modeling"☆36Sep 17, 2026Updated last month
- Official repository of: Attention Sinks in Diffusion Language Models☆12Dec 10, 2025Updated 11 months ago
- Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals; ACL 2024☆13May 24, 2024Updated 2 years ago
- War Games measures whether frontier models can sustain long-horizon planning and adaptation in complex, non-stationary real-time games, w…☆15May 5, 2026Updated 6 months ago
- ☆14Oct 6, 2026Updated last month
- ☆96Oct 19, 2026Updated 3 weeks ago
- Official Implementation of "DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucination"☆30Dec 18, 2024Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆18Sep 28, 2026Updated last month
- Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents☆31Apr 16, 2026Updated 6 months ago
- Code2Bench: Scaling Source and Rigor for Dynamic Benchmark Construction☆10Feb 6, 2026Updated 9 months ago
- MCP server for interactive terminal sessions — local shells, SSH, serial ports, and persistent remote sessions☆20Oct 22, 2026Updated 3 weeks ago
- (ACL 2025) Divide-Then-Aggregate: An Efficient Tool Learning Method via Parallel Tool Invocation☆12May 21, 2025Updated last year
- ☆11Jul 14, 2025Updated last year
- ☆10May 16, 2026Updated 5 months ago
- Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection Learning (KDD '25)☆12May 30, 2025Updated last year
- Local mission-control dashboard for Codex, OpenCode, Claude Code, and compatible agent sessions.☆18Aug 21, 2026Updated 2 months ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Reproduction package for "Harness as a Language: A Minimalist Agent Framework With Maximal Expressivity" — ten agent arms across AppWorld…☆36Oct 10, 2026Updated last month
- [EMNLP'26 Findings] Triplet-Block Diffusion RWKV☆15May 26, 2026Updated 5 months ago
- Code for 'Answer Matching Outperforms Multiple Choice for Language Model Evaluation' paper☆20Jul 4, 2025Updated last year
- 🔍 一键检测 AI API 服务商是否如实提供所标注的模型 | 支持 OpenAI / Claude / Gemini / DeepSeek 等 9 大模型原厂对比验证☆22Mar 6, 2026Updated 8 months ago
- Repository for "Training Language Models To Explain Their Own Computations"☆42Jul 7, 2026Updated 4 months ago
- Internal projen project types used by the CDK team. No support offered, use at your own risk.☆13Updated this week
- ☆12Oct 27, 2026Updated 2 weeks ago
- [EMNLP2026 Findings] TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectories☆21Sep 7, 2026Updated 2 months ago
- CatchBench: a benchmark for auditing agent failures across the full lifecycle.☆12Oct 26, 2026Updated 2 weeks ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- RepoZero: Can LLMs Generate a Code Repository from Scratch? (https://arxiv.org/abs/2605.07122)☆36Oct 15, 2026Updated 3 weeks ago
- ☆55Sep 18, 2026Updated last month
- Hosted persistent memory for AI agents over MCP. Tell it a recalled memory helped or misled, and it re-ranks what comes back next. Shared…☆28Updated this week
- Fused KL divergence from hidden states for knowledge distillation☆22Apr 28, 2026Updated 6 months ago
- ☆16Jun 4, 2025Updated last year
- Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models☆16Oct 3, 2026Updated last month
- Official repo for ”Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought“☆29Mar 29, 2026Updated 7 months ago
Are these results useful?