Skip to content
The Daily Repo

Gloriaameng / Awesome-Agent-Harness

The first survey dedicated to LLM agent harnesses — 168 references, 34 evidence-coded systems, and 30 evaluation entries.

Why this job: name: awesome; topics: awesome-list

Agent harness architecture: execution, tools, context, state, lifecycle and evidence

What it does

  • MemGPT. Tiered memory and context management inspired by operating systems.
  • Reflexion. Verbal feedback and reflective memory across trials.
  • Voyager. Open-ended skill acquisition, curriculum generation, and reusable code skills.
  • Generative Agents. Memory, reflection, and planning for believable social agents.
  • Concordia. A library for generative agent-based simulations grounded in physical, social, or digital worlds.

Get started

No single install command. Read the steps in the README (opens in new tab)

Maintenance
Active
Last commit yesterday
Stars
379
+2 this week
Licence
CC-BY-4.0
Read the terms
Downloads for
None listed
No release files
Latest version
None yet
No releases
Built with
Python
100% of the code

Is it looked after?

Contributors
21
Last 90 days
Issues
80% closed
2 still open
Pull requests
29 merged
1 waiting
Releases
None
Never published
  • No contributing guide
  • No security policy
  • No code of conduct

Similar repos

Repos similar to this one
RepoStarsLast commitLicenceDownloads for
RyanAlberts / best-of-Agent-Harnesses1,4892 days agoCC-BY-SA-4.0No downloads
walkinglabs / awesome-harness-engineering4,672yesterdayCC0-1.0No downloads
hardness1020 / learn-agent-architecture1,21220 days agoMITNo downloads
More: languages, topics and project record

Languages

  • Python 100%

Topics

  • agent
  • agent-framework
  • agent-harness
  • awesome-list
  • harness
  • harness-engineering
  • llm

Project record

  • JobLists and guides
  • StatusListed
  • Commits118
  • Forks39
  • Watching5
  • Stars in 28 days+10
  • CreatedApr 3, 2026
  • First seen by usNov 7, 2026
  • CheckedNov 10, 2026

Type to search.

Try