Highlighted
Open highlighted repo slot
Put your repository first
Promote a GitHub repo at the top of Awesome repository list views for 7 days.
Awesome List
Awesome Harness Engineering
Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.
ai-boost/awesome-harness-engineering
#agent-harness
#agent-memory
#agent-orchestration
#ai-agent-harness
#ai-agents
#awesome-list
#context-engineering
#harness-engineering
#mcp
- List stars
- 3,108
- README repos
- 184
- Indexed repos
- 141
- List commits
- 108
- Forks
- 333
- Open issues
- 105
Tracked list growth
GitHub stars and default-branch commits for ai-boost/awesome-harness-engineering.
Latest scan 2026-07-17 10:49
Likes history
GitHub starsCommits history
Default branch commits
Latest repo push 2026-07-17
kubernetes-sigs/agent-sandbox
agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes.
AI dev
- Updated
- 2026-07-15
- Lists
- 2 list mentions
- First commit
- 2025-08-12
- License
- Apache-2.0
- Issues
- 212 open
3,155
stars
- Forks
- 405
- Commits
- 689 commits
- Star growth, last 7 days
- 0 0.0%
- Commit velocity, last 7 days
- 0 0.0%
bradygaster/squad
Squad: AI agent teams for any project
AI dev
Stack
GitHub topics
- Updated
- 2026-07-10
- Lists
- 1 list mention
- First commit
- 2026-02-06
- License
- MIT
- Issues
- 105 open
2,968
stars
- Forks
- 451
- Commits
- 1,833 commits
- Star growth, last 7 days
- 0 0.0%
- Commit velocity, last 7 days
- 0 0.0%
UKGovernmentBEIS/inspect_ai
Inspect: A framework for large language model evaluations
AI dev
- Updated
- 2026-07-17
- Lists
- 2 list mentions
- First commit
- 2024-05-01
- License
- MIT
- Issues
- 238 open
2,365
stars
- Forks
- 608
- Commits
- 6,747 commits
- Star growth, last 7 days
- +36 +1.5%
- Commit velocity, last 7 days
- +212 +3.2%
future-agi/future-agi
Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.
GitHub topics
- Updated
- 2026-07-14
- Lists
- 5 list mentions
- First commit
- 2026-04-23
- License
- Apache-2.0
- Issues
- 456 open
1,406
stars
- Forks
- 389
- Commits
- 1,306 commits
- Star growth, last 7 days
- 0 0.0%
- Commit velocity, last 7 days
- 0 0.0%
ZJU-REAL/ClawGUI
Build, Evaluate, and Deploy GUI Agents — online RL training, standardized benchmarks, and real-device deployment in one framework.
AI dev
GitHub topics
- Updated
- 2026-06-03
- Lists
- 1 list mention
- First commit
- 2026-03-26
- License
- Apache-2.0
- Issues
- 2 open
1,311
stars
- Forks
- 52
- Commits
- 211 commits
- Star growth, last 7 days
- 0 0.0%
- Commit velocity, last 7 days
- 0 0.0%
stanford-iris-lab/meta-harness
Reference code for the Meta-Harness paper.
GitHub topics
- Updated
- 2026-07-11
- Lists
- 2 list mentions
- First commit
- 2026-04-15
- License
- MIT
- Issues
- 4 open
1,271
stars
- Forks
- 123
- Commits
- 18 commits
- Star growth, last 7 days
- 0 0.0%
- Commit velocity, last 7 days
- 0 0.0%
greyhaven-ai/autocontext
a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task
AI dev
GitHub topics
- Updated
- 2026-07-12
- Lists
- 1 list mention
- First commit
- 2026-02-12
- License
- Apache-2.0
- Issues
- 0 open
1,243
stars
- Forks
- 102
- Commits
- 1,962 commits
- Star growth, last 7 days
- 0 0.0%
- Commit velocity, last 7 days
- 0 0.0%
wandb/weave
Weave is a toolkit for developing AI-powered applications, built by Weights & Biases.
AI dev
- Updated
- 2026-07-12
- Lists
- 2 list mentions
- First commit
- 2022-03-23
- License
- Apache-2.0
- Issues
- 299 open
1,104
stars
- Forks
- 157
- Commits
- 7,072 commits
- Star growth, last 7 days
- 0 0.0%
- Commit velocity, last 7 days
- 0 0.0%
Mibayy/token-savior
The MCP server that turns Claude into the only coding agent hitting 100% on a real benchmark. -77% active tokens, -76% wall time, 0 losses across 96 tasks on Claude Opus 4.7. Structural code navigation + persistent memory. Works with every MCP client.
AI dev
- Updated
- 2026-07-04
- Lists
- 2 list mentions
- First commit
- 2026-03-25
- License
- MIT
- Issues
- 9 open
1,064
stars
- Forks
- 88
- Commits
- 357 commits
- Star growth, last 7 days
- 0 0.0%
- Commit velocity, last 7 days
- 0 0.0%
rasbt/mini-coding-agent
Minimal and readable coding agent harness implementation in Python to explain the core components of coding agents.
- Updated
- 2026-04-07
- Lists
- 2 list mentions
- First commit
- 2026-04-02
- License
- Apache-2.0
- Issues
- 2 open
1,010
stars
- Forks
- 184
- Commits
- 15 commits
- Star growth, last 7 days
- 0 0.0%
- Commit velocity, last 7 days
- 0 0.0%
agentscope-ai/agentscope-runtime
A production-ready runtime framework for agent apps with secure tool sandboxing, Agent-as-a-Service APIs, scalable deployment, full-stack observability, and broad framework compatibility.
AI dev
GitHub topics
- Updated
- 2026-06-04
- Lists
- 2 list mentions
- First commit
- 2025-08-14
- License
- Apache-2.0
- Issues
- 72 open
- Forks
- 163
- Commits
- 290 commits
- Star growth, last 7 days
- 0 0.0%
- Commit velocity, last 7 days
- 0 0.0%
claw-eval/claw-eval
Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.
- Updated
- 2026-05-17
- Lists
- 2 list mentions
- First commit
- 2026-03-17
- License
- Unknown
- Issues
- 19 open
716
stars
- Forks
- 64
- Commits
- 43 commits
- Star growth, last 7 days
- 0 0.0%
- Commit velocity, last 7 days
- 0 0.0%
sipyourdrink-ltd/bernstein
Audit-grade multi-agent orchestration for CLI coding agents (Claude Code, Codex, Gemini CLI, +40 more). HMAC-chained audit log, signed agent cards, per-artefact lineage, air-gap deploy. The orchestrator your compliance team will sign off on. https://bernstein.run
AI dev
GitHub topics
- Updated
- 2026-07-01
- Lists
- 6 list mentions
- First commit
- 2026-03-27
- License
- Apache-2.0
- Issues
- 11 open
- Forks
- 56
- Commits
- 3,311 commits
- Star growth, last 7 days
- No 7-day history
- Commit velocity, last 7 days
- No 7-day history
manuelschipper/nah
You should sandbox your agents. This is for when you don't.
AI dev
- Updated
- 2026-06-30
- Lists
- 1 list mention
- First commit
- 2026-03-10
- License
- MIT
- Issues
- 6 open
452
stars
- Forks
- 26
- Commits
- 881 commits
- Star growth, last 7 days
- 0 0.0%
- Commit velocity, last 7 days
- 0 0.0%
rotorstar/hitl-protocol
Human-in-the-Loop Protocol for Autonomous Agent Services — Open Standard (v0.8)
GitHub topics
- Updated
- 2026-07-11
- Lists
- 1 list mention
- First commit
- 2026-02-23
- License
- Apache-2.0
- Issues
- 1 open
- Forks
- 0
- Commits
- 43 commits
- Star growth, last 7 days
- 0 0.0%
- Commit velocity, last 7 days
- 0 0.0%