we have incredible tools for writing and shipping code
but understanding what coding agents do along the way is a different problem
AgentPlay makes the entire session EXPLORABLE.
but understanding what coding agents do along the way is a different problem
AgentPlay makes the entire session EXPLORABLE.
4
1
18
521
AgentPlay now reads Gemini CLI sessions 🚀
Replay what your Gemini agent read, edited and broke, right next to your Claude Code, Codex, Cursor and Copilot runs
Shoutout to @shubhook for the parser github.com/Entelligence-A…
Replay what your Gemini agent read, edited and broke, right next to your Claude Code, Codex, Cursor and Copilot runs
Shoutout to @shubhook for the parser github.com/Entelligence-A…
15
2
23
601
Super excited to have you join the team @MattsSchtick!
Matt joins us with over 20 years of experience leading enterprise sales teams across Zendesk, SullyAI, Prezi and AnswerIQ.
He's picked up the entire platform in days, has lead both PLG and sales led motions at scale and ce working at early stage and growth stage companies.
We're super excited to see you lead our growth and sales org!
Matt joins us with over 20 years of experience leading enterprise sales teams across Zendesk, SullyAI, Prezi and AnswerIQ.
He's picked up the entire platform in days, has lead both PLG and sales led motions at scale and ce working at early stage and growth stage companies.
We're super excited to see you lead our growth and sales org!
1
1
12
1,093
Entelligence AI retweeted
Engineering leaders are all running into the same process and road blocks with optimizing their engineering agents -
1. Get cost visibility and basic engineer level caps
2. Build an ad hoc system to try to trace it to ROI
3. Face challenges before getting to a unified learning roach to these challenges at the Silicon Valley AI hub! Thanks to @shilpinayak
1. Get cost visibility and basic engineer level caps
2. Build an ad hoc system to try to trace it to ROI
3. Face challenges before getting to a unified learning roach to these challenges at the Silicon Valley AI hub! Thanks to @shilpinayak
2
2
13
575
LangSmith tracks LLM traces. Langfuse brings observability to LLM apps.
we wanted a more VISUAL way to explore and replay coding agent sessions
so we built AgentPlay.
we wanted a more VISUAL way to explore and replay coding agent sessions
so we built AgentPlay.
7
1
12
495
Entelligence AI retweeted
want to help make AgentPlay support more coding agents?
we've opened up issues for Windsurf, Amp, Roo Code, Cline, Aider and Gemini CLI
if you use any of these, we'd love your contributions 👇
we've opened up issues for Windsurf, Amp, Roo Code, Cline, Aider and Gemini CLI
if you use any of these, we'd love your contributions 👇
AgentPlay is open source, and we're adding support for more coding agents
just opened issues for Windsurf, Amp, Roo Code, Cline, Aider and Gemini CLI
if you use any of these, we'd love a hand getting them supported
0
2
11
454
want to help make AgentPlay support more coding agents?
we've opened up issues for Windsurf, Amp, Roo Code, Cline, Aider and Gemini CLI
if you use any of these, we'd love your contributions 👇
we've opened up issues for Windsurf, Amp, Roo Code, Cline, Aider and Gemini CLI
if you use any of these, we'd love your contributions 👇
AgentPlay is open source, and we're adding support for more coding agents
just opened issues for Windsurf, Amp, Roo Code, Cline, Aider and Gemini CLI
if you use any of these, we'd love a hand getting them supported
0
2
11
454
Entelligence AI retweeted
Entelligence AI open-source agentplay: See and replay your coding agent sessions as a map and a timeline
→ Replay what it read, what it edited, what failed, and what it shipped
→ Local, open source, works across Claude Code, Codex, Cursor, Copilot, OpenCode, and Kiro
→ One to find the agent sessions already on your machine, build a redacted replay of each one, and open a local viewer
More info: aideveloper44.com/product/agentp…
@EntelligenceAI | #opensource #codingagent
→ Replay what it read, what it edited, what failed, and what it shipped
→ Local, open source, works across Claude Code, Codex, Cursor, Copilot, OpenCode, and Kiro
→ One to find the agent sessions already on your machine, build a redacted replay of each one, and open a local viewer
More info: aideveloper44.com/product/agentp…
@EntelligenceAI | #opensource #codingagent
7
1
6
512
Entelligence AI retweeted
coding agents do a LOT behind the scenes
AgentPlay lets you explore and replay the entire session as an interactive map
every tool call, error, file change and subagent, all in one place
AgentPlay is open source. try it out 👇
AgentPlay lets you explore and replay the entire session as an interactive map
every tool call, error, file change and subagent, all in one place
AgentPlay is open source. try it out 👇
29
6
71
3,361
coding agents do a LOT behind the scenes
AgentPlay lets you explore and replay the entire session as an interactive map
every tool call, error, file change and subagent, all in one place
AgentPlay is open source. try it out 👇
AgentPlay lets you explore and replay the entire session as an interactive map
every tool call, error, file change and subagent, all in one place
AgentPlay is open source. try it out 👇
29
6
71
3,361
Entelligence AI retweeted
What's the craziest session you've run?
Seeing some crazy things so far -
- 112 PRs created from 1 session
- 33x compaction in a session
- 44 subagents in a session
github.com/Entelligence-A…
Seeing some crazy things so far -
- 112 PRs created from 1 session
- 33x compaction in a session
- 44 subagents in a session
github.com/Entelligence-A…
2
4
17
822
Entelligence AI retweeted
If an eng burns $1k on a session across 119 hrs but creates 25 PRs from it... 😭
Doing some interesting analysis into how much more or less efficient super long sessions with a lot of PRs are compared to shorter 1 PR sessions
Doing some interesting analysis into how much more or less efficient super long sessions with a lot of PRs are compared to shorter 1 PR sessions
2
2
13
851
Entelligence AI retweeted
Friday evening experimentation 🫡
Huge shoutout to @sumitmishra2026 for the rigor behind our self-improving coding agent harness
20+ experiments a day. Every historical PR comment replayed as an eval case
Nearly 40% of real review comments prevented, up from 13%. 80%+ next!
Huge shoutout to @sumitmishra2026 for the rigor behind our self-improving coding agent harness
20+ experiments a day. Every historical PR comment replayed as an eval case
Nearly 40% of real review comments prevented, up from 13%. 80%+ next!
17
2
29
1,081
Entelligence AI retweeted
continual learning. RSI.
Good times ahead!!
Good times ahead!!
Introducing AgentPlay 🚀
The future of coding is self improving coding agent harnesses that help agents avoid making the same mistakes over and over.
Turn your existing Claude Code, Codex, Cursor and Copilot sessions into interactive maps and replayable timelines.
See what ere it failed, what it retried and how it reached the final change
Free, local and open source.
GitHub: github.com/Entelligence-A…
1
4
17
644
Entelligence AI retweeted
Introducing AgentPlay 🚀
The future of coding is self improving coding agent harnesses that help agents avoid making the same mistakes over and over.
Turn your existing Claude Code, Codex, Cursor and Copilot sessions into interactive maps and replayable timelines.
See what ere it failed, what it retried and how it reached the final change
Free, local and open source.
GitHub: github.com/Entelligence-A…
The future of coding is self improving coding agent harnesses that help agents avoid making the same mistakes over and over.
Turn your existing Claude Code, Codex, Cursor and Copilot sessions into interactive maps and replayable timelines.
See what ere it failed, what it retried and how it reached the final change
Free, local and open source.
GitHub: github.com/Entelligence-A…
115
33
322
82,346
